102 files changed, 2202 insertions, 946 deletions

diff --git a/tools/arch/powerpc/include/uapi/asm/kvm.h b/tools/arch/powerpc/include/uapi/asm/kvm.h
index 637b7263cb86..833ed9a16adf 100644
--- a/tools/arch/powerpc/include/uapi/asm/kvm.h
+++ b/tools/arch/powerpc/include/uapi/asm/kvm.h
@@ -632,6 +632,8 @@ struct kvm_ppc_cpu_char {
 #define KVM_REG_PPC_TIDR        (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xbc)
 #define KVM_REG_PPC_PSSCR       (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xbd)
 
+#define KVM_REG_PPC_DEC_EXPIRY  (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xbe)
+
 /* Transactional Memory checkpointed state:
  * This is all GPRs, all VSX regs and a subset of SPRs
  */
diff --git a/tools/arch/s390/include/uapi/asm/unistd.h b/tools/arch/s390/include/uapi/asm/unistd.h
deleted file mode 100644
index 725120939051..000000000000
--- a/tools/arch/s390/include/uapi/asm/unistd.h
+++ /dev/null
@@ -1,412 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
-/*
- *  S390 version
- *
- *  Derived from "include/asm-i386/unistd.h"
- */
-
-#ifndef _UAPI_ASM_S390_UNISTD_H_
-#define _UAPI_ASM_S390_UNISTD_H_
-
-/*
- * This file contains the system call numbers.
- */
-
-#define __NR_exit                 1
-#define __NR_fork                 2
-#define __NR_read                 3
-#define __NR_write                4
-#define __NR_open                 5
-#define __NR_close                6
-#define __NR_restart_syscall      7
-#define __NR_creat                8
-#define __NR_link                 9
-#define __NR_unlink              10
-#define __NR_execve              11
-#define __NR_chdir               12
-#define __NR_mknod               14
-#define __NR_chmod               15
-#define __NR_lseek               19
-#define __NR_getpid              20
-#define __NR_mount               21
-#define __NR_umount              22
-#define __NR_ptrace              26
-#define __NR_alarm               27
-#define __NR_pause               29
-#define __NR_utime               30
-#define __NR_access              33
-#define __NR_nice                34
-#define __NR_sync                36
-#define __NR_kill                37
-#define __NR_rename              38
-#define __NR_mkdir               39
-#define __NR_rmdir               40
-#define __NR_dup                 41
-#define __NR_pipe                42
-#define __NR_times               43
-#define __NR_brk                 45
-#define __NR_signal              48
-#define __NR_acct                51
-#define __NR_umount2             52
-#define __NR_ioctl               54
-#define __NR_fcntl               55
-#define __NR_setpgid             57
-#define __NR_umask               60
-#define __NR_chroot              61
-#define __NR_ustat               62
-#define __NR_dup2                63
-#define __NR_getppid             64
-#define __NR_getpgrp             65
-#define __NR_setsid              66
-#define __NR_sigaction           67
-#define __NR_sigsuspend          72
-#define __NR_sigpending          73
-#define __NR_sethostname         74
-#define __NR_setrlimit           75
-#define __NR_getrusage           77
-#define __NR_gettimeofday        78
-#define __NR_settimeofday        79
-#define __NR_symlink             83
-#define __NR_readlink            85
-#define __NR_uselib              86
-#define __NR_swapon              87
-#define __NR_reboot              88
-#define __NR_readdir             89
-#define __NR_mmap                90
-#define __NR_munmap              91
-#define __NR_truncate            92
-#define __NR_ftruncate           93
-#define __NR_fchmod              94
-#define __NR_getpriority         96
-#define __NR_setpriority         97
-#define __NR_statfs              99
-#define __NR_fstatfs            100
-#define __NR_socketcall         102
-#define __NR_syslog             103
-#define __NR_setitimer          104
-#define __NR_getitimer          105
-#define __NR_stat               106
-#define __NR_lstat              107
-#define __NR_fstat              108
-#define __NR_lookup_dcookie     110
-#define __NR_vhangup            111
-#define __NR_idle               112
-#define __NR_wait4              114
-#define __NR_swapoff            115
-#define __NR_sysinfo            116
-#define __NR_ipc                117
-#define __NR_fsync              118
-#define __NR_sigreturn          119
-#define __NR_clone              120
-#define __NR_setdomainname      121
-#define __NR_uname              122
-#define __NR_adjtimex           124
-#define __NR_mprotect           125
-#define __NR_sigprocmask        126
-#define __NR_create_module      127
-#define __NR_init_module        128
-#define __NR_delete_module      129
-#define __NR_get_kernel_syms    130
-#define __NR_quotactl           131
-#define __NR_getpgid            132
-#define __NR_fchdir             133
-#define __NR_bdflush            134
-#define __NR_sysfs              135
-#define __NR_personality        136
-#define __NR_afs_syscall        137 /* Syscall for Andrew File System */
-#define __NR_getdents           141
-#define __NR_flock              143
-#define __NR_msync              144
-#define __NR_readv              145
-#define __NR_writev             146
-#define __NR_getsid             147
-#define __NR_fdatasync          148
-#define __NR__sysctl            149
-#define __NR_mlock              150
-#define __NR_munlock            151
-#define __NR_mlockall           152
-#define __NR_munlockall         153
-#define __NR_sched_setparam             154
-#define __NR_sched_getparam             155
-#define __NR_sched_setscheduler         156
-#define __NR_sched_getscheduler         157
-#define __NR_sched_yield                158
-#define __NR_sched_get_priority_max     159
-#define __NR_sched_get_priority_min     160
-#define __NR_sched_rr_get_interval      161
-#define __NR_nanosleep          162
-#define __NR_mremap             163
-#define __NR_query_module       167
-#define __NR_poll               168
-#define __NR_nfsservctl         169
-#define __NR_prctl              172
-#define __NR_rt_sigreturn       173
-#define __NR_rt_sigaction       174
-#define __NR_rt_sigprocmask     175
-#define __NR_rt_sigpending      176
-#define __NR_rt_sigtimedwait    177
-#define __NR_rt_sigqueueinfo    178
-#define __NR_rt_sigsuspend      179
-#define __NR_pread64            180
-#define __NR_pwrite64           181
-#define __NR_getcwd             183
-#define __NR_capget             184
-#define __NR_capset             185
-#define __NR_sigaltstack        186
-#define __NR_sendfile           187
-#define __NR_getpmsg            188
-#define __NR_putpmsg            189
-#define __NR_vfork              190
-#define __NR_pivot_root         217
-#define __NR_mincore            218
-#define __NR_madvise            219
-#define __NR_getdents64         220
-#define __NR_readahead          222
-#define __NR_setxattr           224
-#define __NR_lsetxattr          225
-#define __NR_fsetxattr          226
-#define __NR_getxattr           227
-#define __NR_lgetxattr          228
-#define __NR_fgetxattr          229
-#define __NR_listxattr          230
-#define __NR_llistxattr         231
-#define __NR_flistxattr         232
-#define __NR_removexattr        233
-#define __NR_lremovexattr       234
-#define __NR_fremovexattr       235
-#define __NR_gettid             236
-#define __NR_tkill              237
-#define __NR_futex              238
-#define __NR_sched_setaffinity  239
-#define __NR_sched_getaffinity  240
-#define __NR_tgkill             241
-/* Number 242 is reserved for tux */
-#define __NR_io_setup           243
-#define __NR_io_destroy         244
-#define __NR_io_getevents       245
-#define __NR_io_submit          246
-#define __NR_io_cancel          247
-#define __NR_exit_group         248
-#define __NR_epoll_create       249
-#define __NR_epoll_ctl          250
-#define __NR_epoll_wait         251
-#define __NR_set_tid_address    252
-#define __NR_fadvise64          253
-#define __NR_timer_create       254
-#define __NR_timer_settime      255
-#define __NR_timer_gettime      256
-#define __NR_timer_getoverrun   257
-#define __NR_timer_delete       258
-#define __NR_clock_settime      259
-#define __NR_clock_gettime      260
-#define __NR_clock_getres       261
-#define __NR_clock_nanosleep    262
-/* Number 263 is reserved for vserver */
-#define __NR_statfs64           265
-#define __NR_fstatfs64          266
-#define __NR_remap_file_pages   267
-#define __NR_mbind              268
-#define __NR_get_mempolicy      269
-#define __NR_set_mempolicy      270
-#define __NR_mq_open            271
-#define __NR_mq_unlink          272
-#define __NR_mq_timedsend       273
-#define __NR_mq_timedreceive    274
-#define __NR_mq_notify          275
-#define __NR_mq_getsetattr      276
-#define __NR_kexec_load         277
-#define __NR_add_key            278
-#define __NR_request_key        279
-#define __NR_keyctl             280
-#define __NR_waitid             281
-#define __NR_ioprio_set         282
-#define __NR_ioprio_get         283
-#define __NR_inotify_init       284
-#define __NR_inotify_add_watch  285
-#define __NR_inotify_rm_watch   286
-#define __NR_migrate_pages      287
-#define __NR_openat             288
-#define __NR_mkdirat            289
-#define __NR_mknodat            290
-#define __NR_fchownat           291
-#define __NR_futimesat          292
-#define __NR_unlinkat           294
-#define __NR_renameat           295
-#define __NR_linkat             296
-#define __NR_symlinkat          297
-#define __NR_readlinkat         298
-#define __NR_fchmodat           299
-#define __NR_faccessat          300
-#define __NR_pselect6           301
-#define __NR_ppoll              302
-#define __NR_unshare            303
-#define __NR_set_robust_list    304
-#define __NR_get_robust_list    305
-#define __NR_splice             306
-#define __NR_sync_file_range    307
-#define __NR_tee                308
-#define __NR_vmsplice           309
-#define __NR_move_pages         310
-#define __NR_getcpu             311
-#define __NR_epoll_pwait        312
-#define __NR_utimes             313
-#define __NR_fallocate          314
-#define __NR_utimensat          315
-#define __NR_signalfd           316
-#define __NR_timerfd            317
-#define __NR_eventfd            318
-#define __NR_timerfd_create     319
-#define __NR_timerfd_settime    320
-#define __NR_timerfd_gettime    321
-#define __NR_signalfd4          322
-#define __NR_eventfd2           323
-#define __NR_inotify_init1      324
-#define __NR_pipe2              325
-#define __NR_dup3               326
-#define __NR_epoll_create1      327
-#define __NR_preadv             328
-#define __NR_pwritev            329
-#define __NR_rt_tgsigqueueinfo  330
-#define __NR_perf_event_open    331
-#define __NR_fanotify_init      332
-#define __NR_fanotify_mark      333
-#define __NR_prlimit64          334
-#define __NR_name_to_handle_at  335
-#define __NR_open_by_handle_at  336
-#define __NR_clock_adjtime      337
-#define __NR_syncfs             338
-#define __NR_setns              339
-#define __NR_process_vm_readv   340
-#define __NR_process_vm_writev  341
-#define __NR_s390_runtime_instr 342
-#define __NR_kcmp               343
-#define __NR_finit_module       344
-#define __NR_sched_setattr      345
-#define __NR_sched_getattr      346
-#define __NR_renameat2          347
-#define __NR_seccomp            348
-#define __NR_getrandom          349
-#define __NR_memfd_create       350
-#define __NR_bpf                351
-#define __NR_s390_pci_mmio_write        352
-#define __NR_s390_pci_mmio_read         353
-#define __NR_execveat           354
-#define __NR_userfaultfd        355
-#define __NR_membarrier         356
-#define __NR_recvmmsg           357
-#define __NR_sendmmsg           358
-#define __NR_socket             359
-#define __NR_socketpair         360
-#define __NR_bind               361
-#define __NR_connect            362
-#define __NR_listen             363
-#define __NR_accept4            364
-#define __NR_getsockopt         365
-#define __NR_setsockopt         366
-#define __NR_getsockname        367
-#define __NR_getpeername        368
-#define __NR_sendto             369
-#define __NR_sendmsg            370
-#define __NR_recvfrom           371
-#define __NR_recvmsg            372
-#define __NR_shutdown           373
-#define __NR_mlock2             374
-#define __NR_copy_file_range    375
-#define __NR_preadv2            376
-#define __NR_pwritev2           377
-#define __NR_s390_guarded_storage       378
-#define __NR_statx              379
-#define __NR_s390_sthyi         380
-#define NR_syscalls 381
-
-/* 
- * There are some system calls that are not present on 64 bit, some
- * have a different name although they do the same (e.g. __NR_chown32
- * is __NR_chown on 64 bit).
- */
-#ifndef __s390x__
-
-#define __NR_time                13
-#define __NR_lchown              16
-#define __NR_setuid              23
-#define __NR_getuid              24
-#define __NR_stime               25
-#define __NR_setgid              46
-#define __NR_getgid              47
-#define __NR_geteuid             49
-#define __NR_getegid             50
-#define __NR_setreuid            70
-#define __NR_setregid            71
-#define __NR_getrlimit           76
-#define __NR_getgroups           80
-#define __NR_setgroups           81
-#define __NR_fchown              95
-#define __NR_ioperm             101
-#define __NR_setfsuid           138
-#define __NR_setfsgid           139
-#define __NR__llseek            140
-#define __NR__newselect         142
-#define __NR_setresuid          164
-#define __NR_getresuid          165
-#define __NR_setresgid          170
-#define __NR_getresgid          171
-#define __NR_chown              182
-#define __NR_ugetrlimit         191     /* SuS compliant getrlimit */
-#define __NR_mmap2              192
-#define __NR_truncate64         193
-#define __NR_ftruncate64        194
-#define __NR_stat64             195
-#define __NR_lstat64            196
-#define __NR_fstat64            197
-#define __NR_lchown32           198
-#define __NR_getuid32           199
-#define __NR_getgid32           200
-#define __NR_geteuid32          201
-#define __NR_getegid32          202
-#define __NR_setreuid32         203
-#define __NR_setregid32         204
-#define __NR_getgroups32        205
-#define __NR_setgroups32        206
-#define __NR_fchown32           207
-#define __NR_setresuid32        208
-#define __NR_getresuid32        209
-#define __NR_setresgid32        210
-#define __NR_getresgid32        211
-#define __NR_chown32            212
-#define __NR_setuid32           213
-#define __NR_setgid32           214
-#define __NR_setfsuid32         215
-#define __NR_setfsgid32         216
-#define __NR_fcntl64            221
-#define __NR_sendfile64         223
-#define __NR_fadvise64_64       264
-#define __NR_fstatat64          293
-
-#else
-
-#define __NR_select             142
-#define __NR_getrlimit          191     /* SuS compliant getrlimit */
-#define __NR_lchown             198
-#define __NR_getuid             199
-#define __NR_getgid             200
-#define __NR_geteuid            201
-#define __NR_getegid            202
-#define __NR_setreuid           203
-#define __NR_setregid           204
-#define __NR_getgroups          205
-#define __NR_setgroups          206
-#define __NR_fchown             207
-#define __NR_setresuid          208
-#define __NR_getresuid          209
-#define __NR_setresgid          210
-#define __NR_getresgid          211
-#define __NR_chown              212
-#define __NR_setuid             213
-#define __NR_setgid             214
-#define __NR_setfsuid           215
-#define __NR_setfsgid           216
-#define __NR_newfstatat         293
-
-#endif
-
-#endif /* _UAPI_ASM_S390_UNISTD_H_ */
diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h
index 1d9199e1c2ad..f41079da38c5 100644
--- a/tools/arch/x86/include/asm/cpufeatures.h
+++ b/tools/arch/x86/include/asm/cpufeatures.h
@@ -210,8 +210,10 @@
 
 #define X86_FEATURE_MBA                 ( 7*32+18) /* Memory Bandwidth Allocation */
 #define X86_FEATURE_RSB_CTXSW           ( 7*32+19) /* "" Fill RSB on context switches */
+#define X86_FEATURE_SEV                 ( 7*32+20) /* AMD Secure Encrypted Virtualization */
 
 #define X86_FEATURE_USE_IBPB            ( 7*32+21) /* "" Indirect Branch Prediction Barrier enabled */
+#define X86_FEATURE_USE_IBRS_FW         ( 7*32+22) /* "" Use IBRS during runtime firmware calls */
 
 /* Virtualization flags: Linux defined, word 8 */
 #define X86_FEATURE_TPR_SHADOW          ( 8*32+ 0) /* Intel TPR Shadow */
diff --git a/tools/bpf/bpftool/common.c b/tools/bpf/bpftool/common.c
index 0b482c0070e0..465995281dcd 100644
--- a/tools/bpf/bpftool/common.c
+++ b/tools/bpf/bpftool/common.c
@@ -55,6 +55,10 @@
 
 #include "main.h"
 
+#ifndef BPF_FS_MAGIC
+#define BPF_FS_MAGIC            0xcafe4a11
+#endif
+
 void p_err(const char *fmt, ...)
 {
         va_list ap;
diff --git a/tools/bpf/bpftool/main.c b/tools/bpf/bpftool/main.c
index 3a0396d87c42..185acfa229b5 100644
--- a/tools/bpf/bpftool/main.c
+++ b/tools/bpf/bpftool/main.c
@@ -244,7 +244,7 @@ static int do_batch(int argc, char **argv)
         }
 
         if (errno && errno != ENOENT) {
-                perror("reading batch file failed");
+                p_err("reading batch file failed: %s", strerror(errno));
                 err = -1;
         } else {
                 p_info("processed %d lines", lines);
diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c
index e8e2baaf93c2..e549e329be82 100644
--- a/tools/bpf/bpftool/prog.c
+++ b/tools/bpf/bpftool/prog.c
@@ -774,6 +774,9 @@ static int do_dump(int argc, char **argv)
                               n < 0 ? strerror(errno) : "short write");
                         goto err_free;
                 }
+
+                if (json_output)
+                        jsonw_null(json_wtr);
         } else {
                 if (member_len == &info.jited_prog_len) {
                         const char *name = NULL;
diff --git a/tools/cgroup/Makefile b/tools/cgroup/Makefile
index 860fa151640a..ffca068e4a76 100644
--- a/tools/cgroup/Makefile
+++ b/tools/cgroup/Makefile
@@ -1,7 +1,6 @@
 # SPDX-License-Identifier: GPL-2.0
 # Makefile for cgroup tools
 
-CC = $(CROSS_COMPILE)gcc
 CFLAGS = -Wall -Wextra
 
 all: cgroup_event_listener
diff --git a/tools/gpio/Makefile b/tools/gpio/Makefile
index 805a2c0cf4cd..240eda014b37 100644
--- a/tools/gpio/Makefile
+++ b/tools/gpio/Makefile
@@ -12,8 +12,6 @@ endif
 # (this improves performance and avoids hard-to-debug behaviour);
 MAKEFLAGS += -r
 
-CC = $(CROSS_COMPILE)gcc
-LD = $(CROSS_COMPILE)ld
 CFLAGS += -O2 -Wall -g -D_GNU_SOURCE -I$(OUTPUT)include
 
 ALL_TARGETS := lsgpio gpio-hammer gpio-event-mon
diff --git a/tools/hv/Makefile b/tools/hv/Makefile
index 1139d71fa0cf..5db5e62cebda 100644
--- a/tools/hv/Makefile
+++ b/tools/hv/Makefile
@@ -1,7 +1,6 @@
 # SPDX-License-Identifier: GPL-2.0
 # Makefile for Hyper-V tools
 
-CC = $(CROSS_COMPILE)gcc
 WARNINGS = -Wall -Wextra
 CFLAGS = $(WARNINGS) -g $(shell getconf LFS_CFLAGS)
 
diff --git a/tools/iio/Makefile b/tools/iio/Makefile
index a08e7a47d6a3..332ed2f6c2c2 100644
--- a/tools/iio/Makefile
+++ b/tools/iio/Makefile
@@ -12,8 +12,6 @@ endif
 # (this improves performance and avoids hard-to-debug behaviour);
 MAKEFLAGS += -r
 
-CC = $(CROSS_COMPILE)gcc
-LD = $(CROSS_COMPILE)ld
 CFLAGS += -O2 -Wall -g -D_GNU_SOURCE -I$(OUTPUT)include
 
 ALL_TARGETS := iio_event_monitor lsiio iio_generic_buffer
diff --git a/tools/include/uapi/drm/i915_drm.h b/tools/include/uapi/drm/i915_drm.h
index ac3c6503ca27..536ee4febd74 100644
--- a/tools/include/uapi/drm/i915_drm.h
+++ b/tools/include/uapi/drm/i915_drm.h
@@ -86,6 +86,62 @@ enum i915_mocs_table_index {
         I915_MOCS_CACHED,
 };
 
+/*
+ * Different engines serve different roles, and there may be more than one
+ * engine serving each role. enum drm_i915_gem_engine_class provides a
+ * classification of the role of the engine, which may be used when requesting
+ * operations to be performed on a certain subset of engines, or for providing
+ * information about that group.
+ */
+enum drm_i915_gem_engine_class {
+        I915_ENGINE_CLASS_RENDER        = 0,
+        I915_ENGINE_CLASS_COPY          = 1,
+        I915_ENGINE_CLASS_VIDEO         = 2,
+        I915_ENGINE_CLASS_VIDEO_ENHANCE = 3,
+
+        I915_ENGINE_CLASS_INVALID       = -1
+};
+
+/**
+ * DOC: perf_events exposed by i915 through /sys/bus/event_sources/drivers/i915
+ *
+ */
+
+enum drm_i915_pmu_engine_sample {
+        I915_SAMPLE_BUSY = 0,
+        I915_SAMPLE_WAIT = 1,
+        I915_SAMPLE_SEMA = 2
+};
+
+#define I915_PMU_SAMPLE_BITS (4)
+#define I915_PMU_SAMPLE_MASK (0xf)
+#define I915_PMU_SAMPLE_INSTANCE_BITS (8)
+#define I915_PMU_CLASS_SHIFT \
+        (I915_PMU_SAMPLE_BITS + I915_PMU_SAMPLE_INSTANCE_BITS)
+
+#define __I915_PMU_ENGINE(class, instance, sample) \
+        ((class) << I915_PMU_CLASS_SHIFT | \
+        (instance) << I915_PMU_SAMPLE_BITS | \
+        (sample))
+
+#define I915_PMU_ENGINE_BUSY(class, instance) \
+        __I915_PMU_ENGINE(class, instance, I915_SAMPLE_BUSY)
+
+#define I915_PMU_ENGINE_WAIT(class, instance) \
+        __I915_PMU_ENGINE(class, instance, I915_SAMPLE_WAIT)
+
+#define I915_PMU_ENGINE_SEMA(class, instance) \
+        __I915_PMU_ENGINE(class, instance, I915_SAMPLE_SEMA)
+
+#define __I915_PMU_OTHER(x) (__I915_PMU_ENGINE(0xff, 0xff, 0xf) + 1 + (x))
+
+#define I915_PMU_ACTUAL_FREQUENCY       __I915_PMU_OTHER(0)
+#define I915_PMU_REQUESTED_FREQUENCY    __I915_PMU_OTHER(1)
+#define I915_PMU_INTERRUPTS             __I915_PMU_OTHER(2)
+#define I915_PMU_RC6_RESIDENCY          __I915_PMU_OTHER(3)
+
+#define I915_PMU_LAST I915_PMU_RC6_RESIDENCY
+
 /* Each region is a minimum of 16k, and there are at most 255 of them.
  */
 #define I915_NR_TEX_REGIONS 255 /* table size 2k - maximum due to use
@@ -450,6 +506,27 @@ typedef struct drm_i915_irq_wait {
  */
 #define I915_PARAM_HAS_EXEC_FENCE_ARRAY  49
 
+/*
+ * Query whether every context (both per-file default and user created) is
+ * isolated (insofar as HW supports). If this parameter is not true, then
+ * freshly created contexts may inherit values from an existing context,
+ * rather than default HW values. If true, it also ensures (insofar as HW
+ * supports) that all state set by this context will not leak to any other
+ * context.
+ *
+ * As not every engine across every gen support contexts, the returned
+ * value reports the support of context isolation for individual engines by
+ * returning a bitmask of each engine class set to true if that class supports
+ * isolation.
+ */
+#define I915_PARAM_HAS_CONTEXT_ISOLATION 50
+
+/* Frequency of the command streamer timestamps given by the *_TIMESTAMP
+ * registers. This used to be fixed per platform but from CNL onwards, this
+ * might vary depending on the parts.
+ */
+#define I915_PARAM_CS_TIMESTAMP_FREQUENCY 51
+
 typedef struct drm_i915_getparam {
         __s32 param;
         /*
diff --git a/tools/include/uapi/linux/if_link.h b/tools/include/uapi/linux/if_link.h
index 8616131e2c61..6d9447700e18 100644
--- a/tools/include/uapi/linux/if_link.h
+++ b/tools/include/uapi/linux/if_link.h
@@ -163,6 +163,7 @@ enum {
         IFLA_IF_NETNSID,
         IFLA_CARRIER_UP_COUNT,
         IFLA_CARRIER_DOWN_COUNT,
+        IFLA_NEW_IFINDEX,
         __IFLA_MAX
 };
 
diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h
index 8fb90a0819c3..7b26d4b0b052 100644
--- a/tools/include/uapi/linux/kvm.h
+++ b/tools/include/uapi/linux/kvm.h
@@ -761,6 +761,7 @@ struct kvm_ppc_resize_hpt {
 #define KVM_TRACE_PAUSE           __KVM_DEPRECATED_MAIN_0x07
 #define KVM_TRACE_DISABLE         __KVM_DEPRECATED_MAIN_0x08
 #define KVM_GET_EMULATED_CPUID    _IOWR(KVMIO, 0x09, struct kvm_cpuid2)
+#define KVM_GET_MSR_FEATURE_INDEX_LIST    _IOWR(KVMIO, 0x0a, struct kvm_msr_list)
 
 /*
  * Extension capability list.
@@ -934,6 +935,7 @@ struct kvm_ppc_resize_hpt {
 #define KVM_CAP_S390_AIS_MIGRATION 150
 #define KVM_CAP_PPC_GET_CPU_CHAR 151
 #define KVM_CAP_S390_BPB 152
+#define KVM_CAP_GET_MSR_FEATURES 153
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
@@ -1362,6 +1364,96 @@ struct kvm_s390_ucas_mapping {
 /* Available with KVM_CAP_S390_CMMA_MIGRATION */
 #define KVM_S390_GET_CMMA_BITS      _IOWR(KVMIO, 0xb8, struct kvm_s390_cmma_log)
 #define KVM_S390_SET_CMMA_BITS      _IOW(KVMIO, 0xb9, struct kvm_s390_cmma_log)
+/* Memory Encryption Commands */
+#define KVM_MEMORY_ENCRYPT_OP      _IOWR(KVMIO, 0xba, unsigned long)
+
+struct kvm_enc_region {
+        __u64 addr;
+        __u64 size;
+};
+
+#define KVM_MEMORY_ENCRYPT_REG_REGION    _IOR(KVMIO, 0xbb, struct kvm_enc_region)
+#define KVM_MEMORY_ENCRYPT_UNREG_REGION  _IOR(KVMIO, 0xbc, struct kvm_enc_region)
+
+/* Secure Encrypted Virtualization command */
+enum sev_cmd_id {
+        /* Guest initialization commands */
+        KVM_SEV_INIT = 0,
+        KVM_SEV_ES_INIT,
+        /* Guest launch commands */
+        KVM_SEV_LAUNCH_START,
+        KVM_SEV_LAUNCH_UPDATE_DATA,
+        KVM_SEV_LAUNCH_UPDATE_VMSA,
+        KVM_SEV_LAUNCH_SECRET,
+        KVM_SEV_LAUNCH_MEASURE,
+        KVM_SEV_LAUNCH_FINISH,
+        /* Guest migration commands (outgoing) */
+        KVM_SEV_SEND_START,
+        KVM_SEV_SEND_UPDATE_DATA,
+        KVM_SEV_SEND_UPDATE_VMSA,
+        KVM_SEV_SEND_FINISH,
+        /* Guest migration commands (incoming) */
+        KVM_SEV_RECEIVE_START,
+        KVM_SEV_RECEIVE_UPDATE_DATA,
+        KVM_SEV_RECEIVE_UPDATE_VMSA,
+        KVM_SEV_RECEIVE_FINISH,
+        /* Guest status and debug commands */
+        KVM_SEV_GUEST_STATUS,
+        KVM_SEV_DBG_DECRYPT,
+        KVM_SEV_DBG_ENCRYPT,
+        /* Guest certificates commands */
+        KVM_SEV_CERT_EXPORT,
+
+        KVM_SEV_NR_MAX,
+};
+
+struct kvm_sev_cmd {
+        __u32 id;
+        __u64 data;
+        __u32 error;
+        __u32 sev_fd;
+};
+
+struct kvm_sev_launch_start {
+        __u32 handle;
+        __u32 policy;
+        __u64 dh_uaddr;
+        __u32 dh_len;
+        __u64 session_uaddr;
+        __u32 session_len;
+};
+
+struct kvm_sev_launch_update_data {
+        __u64 uaddr;
+        __u32 len;
+};
+
+
+struct kvm_sev_launch_secret {
+        __u64 hdr_uaddr;
+        __u32 hdr_len;
+        __u64 guest_uaddr;
+        __u32 guest_len;
+        __u64 trans_uaddr;
+        __u32 trans_len;
+};
+
+struct kvm_sev_launch_measure {
+        __u64 uaddr;
+        __u32 len;
+};
+
+struct kvm_sev_guest_status {
+        __u32 handle;
+        __u32 policy;
+        __u32 state;
+};
+
+struct kvm_sev_dbg {
+        __u64 src_uaddr;
+        __u64 dst_uaddr;
+        __u32 len;
+};
 
 #define KVM_DEV_ASSIGN_ENABLE_IOMMU     (1 << 0)
 #define KVM_DEV_ASSIGN_PCI_2_3          (1 << 1)
diff --git a/tools/kvm/kvm_stat/kvm_stat b/tools/kvm/kvm_stat/kvm_stat
index a5684d0968b4..5898c22ba310 100755
--- a/tools/kvm/kvm_stat/kvm_stat
+++ b/tools/kvm/kvm_stat/kvm_stat
@@ -33,7 +33,7 @@ import resource
 import struct
 import re
 import subprocess
-from collections import defaultdict
+from collections import defaultdict, namedtuple
 
 VMX_EXIT_REASONS = {
     'EXCEPTION_NMI':        0,
@@ -228,6 +228,7 @@ IOCTL_NUMBERS = {
 }
 
 ENCODING = locale.getpreferredencoding(False)
+TRACE_FILTER = re.compile(r'^[^\(]*$')
 
 
 class Arch(object):
@@ -260,6 +261,11 @@ class Arch(object):
                     return ArchX86(SVM_EXIT_REASONS)
                 return
 
+    def tracepoint_is_child(self, field):
+        if (TRACE_FILTER.match(field)):
+            return None
+        return field.split('(', 1)[0]
+
 
 class ArchX86(Arch):
     def __init__(self, exit_reasons):
@@ -267,6 +273,10 @@ class ArchX86(Arch):
         self.ioctl_numbers = IOCTL_NUMBERS
         self.exit_reasons = exit_reasons
 
+    def debugfs_is_child(self, field):
+        """ Returns name of parent if 'field' is a child, None otherwise """
+        return None
+
 
 class ArchPPC(Arch):
     def __init__(self):
@@ -282,6 +292,10 @@ class ArchPPC(Arch):
         self.ioctl_numbers['SET_FILTER'] = 0x80002406 | char_ptr_size << 16
         self.exit_reasons = {}
 
+    def debugfs_is_child(self, field):
+        """ Returns name of parent if 'field' is a child, None otherwise """
+        return None
+
 
 class ArchA64(Arch):
     def __init__(self):
@@ -289,6 +303,10 @@ class ArchA64(Arch):
         self.ioctl_numbers = IOCTL_NUMBERS
         self.exit_reasons = AARCH64_EXIT_REASONS
 
+    def debugfs_is_child(self, field):
+        """ Returns name of parent if 'field' is a child, None otherwise """
+        return None
+
 
 class ArchS390(Arch):
     def __init__(self):
@@ -296,6 +314,12 @@ class ArchS390(Arch):
         self.ioctl_numbers = IOCTL_NUMBERS
         self.exit_reasons = None
 
+    def debugfs_is_child(self, field):
+        """ Returns name of parent if 'field' is a child, None otherwise """
+        if field.startswith('instruction_'):
+            return 'exit_instruction'
+
+
 ARCH = Arch.get_arch()
 
 
@@ -331,9 +355,6 @@ class perf_event_attr(ctypes.Structure):
 PERF_TYPE_TRACEPOINT = 2
 PERF_FORMAT_GROUP = 1 << 3
 
-PATH_DEBUGFS_TRACING = '/sys/kernel/debug/tracing'
-PATH_DEBUGFS_KVM = '/sys/kernel/debug/kvm'
-
 
 class Group(object):
     """Represents a perf event group."""
@@ -376,8 +397,8 @@ class Event(object):
         self.syscall = self.libc.syscall
         self.name = name
         self.fd = None
-        self.setup_event(group, trace_cpu, trace_pid, trace_point,
-                         trace_filter, trace_set)
+        self._setup_event(group, trace_cpu, trace_pid, trace_point,
+                          trace_filter, trace_set)
 
     def __del__(self):
         """Closes the event's file descriptor.
@@ -390,7 +411,7 @@ class Event(object):
         if self.fd:
             os.close(self.fd)
 
-    def perf_event_open(self, attr, pid, cpu, group_fd, flags):
+    def _perf_event_open(self, attr, pid, cpu, group_fd, flags):
         """Wrapper for the sys_perf_evt_open() syscall.
 
         Used to set up performance events, returns a file descriptor or -1
@@ -409,7 +430,7 @@ class Event(object):
                             ctypes.c_int(pid), ctypes.c_int(cpu),
                             ctypes.c_int(group_fd), ctypes.c_long(flags))
 
-    def setup_event_attribute(self, trace_set, trace_point):
+    def _setup_event_attribute(self, trace_set, trace_point):
         """Returns an initialized ctype perf_event_attr struct."""
 
         id_path = os.path.join(PATH_DEBUGFS_TRACING, 'events', trace_set,
@@ -419,8 +440,8 @@ class Event(object):
         event_attr.config = int(open(id_path).read())
         return event_attr
 
-    def setup_event(self, group, trace_cpu, trace_pid, trace_point,
-                    trace_filter, trace_set):
+    def _setup_event(self, group, trace_cpu, trace_pid, trace_point,
+                     trace_filter, trace_set):
         """Sets up the perf event in Linux.
 
         Issues the syscall to register the event in the kernel and
@@ -428,7 +449,7 @@ class Event(object):
 
         """
 
-        event_attr = self.setup_event_attribute(trace_set, trace_point)
+        event_attr = self._setup_event_attribute(trace_set, trace_point)
 
         # First event will be group leader.
         group_leader = -1
@@ -437,8 +458,8 @@ class Event(object):
         if group.events:
             group_leader = group.events[0].fd
 
-        fd = self.perf_event_open(event_attr, trace_pid,
-                                  trace_cpu, group_leader, 0)
+        fd = self._perf_event_open(event_attr, trace_pid,
+                                   trace_cpu, group_leader, 0)
         if fd == -1:
             err = ctypes.get_errno()
             raise OSError(err, os.strerror(err),
@@ -475,6 +496,10 @@ class Event(object):
 
 class Provider(object):
     """Encapsulates functionalities used by all providers."""
+    def __init__(self, pid):
+        self.child_events = False
+        self.pid = pid
+
     @staticmethod
     def is_field_wanted(fields_filter, field):
         """Indicate whether field is valid according to fields_filter."""
@@ -500,12 +525,12 @@ class TracepointProvider(Provider):
     """
     def __init__(self, pid, fields_filter):
         self.group_leaders = []
-        self.filters = self.get_filters()
+        self.filters = self._get_filters()
         self.update_fields(fields_filter)
-        self.pid = pid
+        super(TracepointProvider, self).__init__(pid)
 
     @staticmethod
-    def get_filters():
+    def _get_filters():
         """Returns a dict of trace events, their filter ids and
         the values that can be filtered.
 
@@ -521,8 +546,8 @@ class TracepointProvider(Provider):
             filters['kvm_exit'] = ('exit_reason', ARCH.exit_reasons)
         return filters
 
-    def get_available_fields(self):
-        """Returns a list of available event's of format 'event name(filter
+    def _get_available_fields(self):
+        """Returns a list of available events of format 'event name(filter
         name)'.
 
         All available events have directories under
@@ -549,11 +574,12 @@ class TracepointProvider(Provider):
 
     def update_fields(self, fields_filter):
         """Refresh fields, applying fields_filter"""
-        self.fields = [field for field in self.get_available_fields()
-                       if self.is_field_wanted(fields_filter, field)]
+        self.fields = [field for field in self._get_available_fields()
+                       if self.is_field_wanted(fields_filter, field) or
+                       ARCH.tracepoint_is_child(field)]
 
     @staticmethod
-    def get_online_cpus():
+    def _get_online_cpus():
         """Returns a list of cpu id integers."""
         def parse_int_list(list_string):
             """Returns an int list from a string of comma separated integers and
@@ -575,17 +601,17 @@ class TracepointProvider(Provider):
             cpu_string = cpu_list.readline()
             return parse_int_list(cpu_string)
 
-    def setup_traces(self):
+    def _setup_traces(self):
         """Creates all event and group objects needed to be able to retrieve
         data."""
-        fields = self.get_available_fields()
+        fields = self._get_available_fields()
         if self._pid > 0:
             # Fetch list of all threads of the monitored pid, as qemu
             # starts a thread for each vcpu.
             path = os.path.join('/proc', str(self._pid), 'task')
             groupids = self.walkdir(path)[1]
         else:
-            groupids = self.get_online_cpus()
+            groupids = self._get_online_cpus()
 
         # The constant is needed as a buffer for python libs, std
         # streams and other files that the script opens.
@@ -663,7 +689,7 @@ class TracepointProvider(Provider):
         # The garbage collector will get rid of all Event/Group
         # objects and open files after removing the references.
         self.group_leaders = []
-        self.setup_traces()
+        self._setup_traces()
         self.fields = self._fields
 
     def read(self, by_guest=0):
@@ -671,8 +697,12 @@ class TracepointProvider(Provider):
         ret = defaultdict(int)
         for group in self.group_leaders:
             for name, val in group.read().items():
-                if name in self._fields:
-                    ret[name] += val
+                if name not in self._fields:
+                    continue
+                parent = ARCH.tracepoint_is_child(name)
+                if parent:
+                    name += ' ' + parent
+                ret[name] += val
         return ret
 
     def reset(self):
@@ -690,11 +720,11 @@ class DebugfsProvider(Provider):
         self._baseline = {}
         self.do_read = True
         self.paths = []
-        self.pid = pid
+        super(DebugfsProvider, self).__init__(pid)
         if include_past:
-            self.restore()
+            self._restore()
 
-    def get_available_fields(self):
+    def _get_available_fields(self):
         """"Returns a list of available fields.
 
         The fields are all available KVM debugfs files
@@ -704,8 +734,9 @@ class DebugfsProvider(Provider):
 
     def update_fields(self, fields_filter):
         """Refresh fields, applying fields_filter"""
-        self._fields = [field for field in self.get_available_fields()
-                        if self.is_field_wanted(fields_filter, field)]
+        self._fields = [field for field in self._get_available_fields()
+                        if self.is_field_wanted(fields_filter, field) or
+                        ARCH.debugfs_is_child(field)]
 
     @property
     def fields(self):
@@ -758,7 +789,7 @@ class DebugfsProvider(Provider):
                     paths.append(dir)
         for path in paths:
             for field in self._fields:
-                value = self.read_field(field, path)
+                value = self._read_field(field, path)
                 key = path + field
                 if reset == 1:
                     self._baseline[key] = value
@@ -766,20 +797,21 @@ class DebugfsProvider(Provider):
                     self._baseline[key] = 0
                 if self._baseline.get(key, -1) == -1:
                     self._baseline[key] = value
-                increment = (results.get(field, 0) + value -
-                             self._baseline.get(key, 0))
-                if by_guest:
-                    pid = key.split('-')[0]
-                    if pid in results:
-                        results[pid] += increment
-                    else:
-                        results[pid] = increment
+                parent = ARCH.debugfs_is_child(field)
+                if parent:
+                    field = field + ' ' + parent
+                else:
+                    if by_guest:
+                        field = key.split('-')[0]    # set 'field' to 'pid'
+                increment = value - self._baseline.get(key, 0)
+                if field in results:
+                    results[field] += increment
                 else:
                     results[field] = increment
 
         return results
 
-    def read_field(self, field, path):
+    def _read_field(self, field, path):
         """Returns the value of a single field from a specific VM."""
         try:
             return int(open(os.path.join(PATH_DEBUGFS_KVM,
@@ -794,12 +826,15 @@ class DebugfsProvider(Provider):
         self._baseline = {}
         self.read(1)
 
-    def restore(self):
+    def _restore(self):
         """Reset field counters"""
         self._baseline = {}
         self.read(2)
 
 
+EventStat = namedtuple('EventStat', ['value', 'delta'])
+
+
 class Stats(object):
     """Manages the data providers and the data they provide.
 
@@ -808,13 +843,13 @@ class Stats(object):
 
     """
     def __init__(self, options):
-        self.providers = self.get_providers(options)
+        self.providers = self._get_providers(options)
         self._pid_filter = options.pid
         self._fields_filter = options.fields
         self.values = {}
+        self._child_events = False
 
-    @staticmethod
-    def get_providers(options):
+    def _get_providers(self, options):
         """Returns a list of data providers depending on the passed options."""
         providers = []
 
@@ -826,7 +861,7 @@ class Stats(object):
 
         return providers
 
-    def update_provider_filters(self):
+    def _update_provider_filters(self):
         """Propagates fields filters to providers."""
         # As we reset the counters when updating the fields we can
         # also clear the cache of old values.
@@ -847,7 +882,7 @@ class Stats(object):
     def fields_filter(self, fields_filter):
         if fields_filter != self._fields_filter:
             self._fields_filter = fields_filter
-            self.update_provider_filters()
+            self._update_provider_filters()
 
     @property
     def pid_filter(self):
@@ -861,16 +896,33 @@ class Stats(object):
             for provider in self.providers:
                 provider.pid = self._pid_filter
 
+    @property
+    def child_events(self):
+        return self._child_events
+
+    @child_events.setter
+    def child_events(self, val):
+        self._child_events = val
+        for provider in self.providers:
+            provider.child_events = val
+
     def get(self, by_guest=0):
         """Returns a dict with field -> (value, delta to last value) of all
-        provider data."""
+        provider data.
+        Key formats:
+          * plain: 'key' is event name
+          * child-parent: 'key' is in format '<child> <parent>'
+          * pid: 'key' is the pid of the guest, and the record contains the
+               aggregated event data
+        These formats are generated by the providers, and handled in class TUI.
+        """
         for provider in self.providers:
             new = provider.read(by_guest=by_guest)
-            for key in new if by_guest else provider.fields:
-                oldval = self.values.get(key, (0, 0))[0]
+            for key in new:
+                oldval = self.values.get(key, EventStat(0, 0)).value
                 newval = new.get(key, 0)
                 newdelta = newval - oldval
-                self.values[key] = (newval, newdelta)
+                self.values[key] = EventStat(newval, newdelta)
         return self.values
 
     def toggle_display_guests(self, to_pid):
@@ -899,10 +951,10 @@ class Stats(object):
         self.get(to_pid)
         return 0
 
+
 DELAY_DEFAULT = 3.0
 MAX_GUEST_NAME_LEN = 48
 MAX_REGEX_LEN = 44
-DEFAULT_REGEX = r'^[^\(]*$'
 SORT_DEFAULT = 0
 
 
@@ -969,7 +1021,7 @@ class Tui(object):
 
         return res
 
-    def print_all_gnames(self, row):
+    def _print_all_gnames(self, row):
         """Print a list of all running guests along with their pids."""
         self.screen.addstr(row, 2, '%8s  %-60s' %
                            ('Pid', 'Guest Name (fuzzy list, might be '
@@ -1032,19 +1084,13 @@ class Tui(object):
 
         return name
 
-    def update_drilldown(self):
-        """Sets or removes a filter that only allows fields without braces."""
-        if not self.stats.fields_filter:
-            self.stats.fields_filter = DEFAULT_REGEX
-
-        elif self.stats.fields_filter == DEFAULT_REGEX:
-            self.stats.fields_filter = None
-
-    def update_pid(self, pid):
+    def _update_pid(self, pid):
         """Propagates pid selection to stats object."""
+        self.screen.addstr(4, 1, 'Updating pid filter...')
+        self.screen.refresh()
         self.stats.pid_filter = pid
 
-    def refresh_header(self, pid=None):
+    def _refresh_header(self, pid=None):
         """Refreshes the header."""
         if pid is None:
             pid = self.stats.pid_filter
@@ -1059,8 +1105,7 @@ class Tui(object):
                                .format(pid, gname), curses.A_BOLD)
         else:
             self.screen.addstr(0, 0, 'kvm statistics - summary', curses.A_BOLD)
-        if self.stats.fields_filter and self.stats.fields_filter \
-           != DEFAULT_REGEX:
+        if self.stats.fields_filter:
             regex = self.stats.fields_filter
             if len(regex) > MAX_REGEX_LEN:
                 regex = regex[:MAX_REGEX_LEN] + '...'
@@ -1075,56 +1120,99 @@ class Tui(object):
         self.screen.addstr(4, 1, 'Collecting data...')
         self.screen.refresh()
 
-    def refresh_body(self, sleeptime):
+    def _refresh_body(self, sleeptime):
+        def is_child_field(field):
+            return field.find('(') != -1
+
+        def insert_child(sorted_items, child, values, parent):
+            num = len(sorted_items)
+            for i in range(0, num):
+                # only add child if parent is present
+                if parent.startswith(sorted_items[i][0]):
+                    sorted_items.insert(i + 1, ('  ' + child, values))
+
+        def get_sorted_events(self, stats):
+            """ separate parent and child events """
+            if self._sorting == SORT_DEFAULT:
+                def sortkey((_k, v)):
+                    # sort by (delta value, overall value)
+                    return (v.delta, v.value)
+            else:
+                def sortkey((_k, v)):
+                    # sort by overall value
+                    return v.value
+
+            childs = []
+            sorted_items = []
+            # we can't rule out child events to appear prior to parents even
+            # when sorted - separate out all children first, and add in later
+            for key, values in sorted(stats.items(), key=sortkey,
+                                      reverse=True):
+                if values == (0, 0):
+                    continue
+                if key.find(' ') != -1:
+                    if not self.stats.child_events:
+                        continue
+                    childs.insert(0, (key, values))
+                else:
+                    sorted_items.append((key, values))
+            if self.stats.child_events:
+                for key, values in childs:
+                    (child, parent) = key.split(' ')
+                    insert_child(sorted_items, child, values, parent)
+
+            return sorted_items
+
         row = 3
         self.screen.move(row, 0)
         self.screen.clrtobot()
         stats = self.stats.get(self._display_guests)
-
-        def sortCurAvg(x):
-            # sort by current events if available
-            if stats[x][1]:
-                return (-stats[x][1], -stats[x][0])
+        total = 0.
+        ctotal = 0.
+        for key, values in stats.items():
+            if self._display_guests:
+                if self.get_gname_from_pid(key):
+                    total += values.value
+                continue
+            if not key.find(' ') != -1:
+                total += values.value
             else:
-                return (0, -stats[x][0])
+                ctotal += values.value
+        if total == 0.:
+            # we don't have any fields, or all non-child events are filtered
+            total = ctotal
 
-        def sortTotal(x):
-            # sort by totals
-            return (0, -stats[x][0])
-        total = 0.
-        for key in stats.keys():
-            if key.find('(') is -1:
-                total += stats[key][0]
-        if self._sorting == SORT_DEFAULT:
-            sortkey = sortCurAvg
-        else:
-            sortkey = sortTotal
+        # print events
         tavg = 0
-        for key in sorted(stats.keys(), key=sortkey):
-            if row >= self.screen.getmaxyx()[0] - 1:
-                break
-            values = stats[key]
-            if not values[0] and not values[1]:
+        tcur = 0
+        for key, values in get_sorted_events(self, stats):
+            if row >= self.screen.getmaxyx()[0] - 1 or values == (0, 0):
                 break
-            if values[0] is not None:
-                cur = int(round(values[1] / sleeptime)) if values[1] else ''
-                if self._display_guests:
-                    key = self.get_gname_from_pid(key)
-                self.screen.addstr(row, 1, '%-40s %10d%7.1f %8s' %
-                                   (key, values[0], values[0] * 100 / total,
-                                    cur))
-                if cur is not '' and key.find('(') is -1:
-                    tavg += cur
+            if self._display_guests:
+                key = self.get_gname_from_pid(key)
+                if not key:
+                    continue
+            cur = int(round(values.delta / sleeptime)) if values.delta else ''
+            if key[0] != ' ':
+                if values.delta:
+                    tcur += values.delta
+                ptotal = values.value
+                ltotal = total
+            else:
+                ltotal = ptotal
+            self.screen.addstr(row, 1, '%-40s %10d%7.1f %8s' % (key,
+                               values.value,
+                               values.value * 100 / float(ltotal), cur))
             row += 1
         if row == 3:
             self.screen.addstr(4, 1, 'No matching events reported yet')
-        else:
+        if row > 4:
+            tavg = int(round(tcur / sleeptime)) if tcur > 0 else ''
             self.screen.addstr(row, 1, '%-40s %10d        %8s' %
-                               ('Total', total, tavg if tavg else ''),
-                               curses.A_BOLD)
+                               ('Total', total, tavg), curses.A_BOLD)
         self.screen.refresh()
 
-    def show_msg(self, text):
+    def _show_msg(self, text):
         """Display message centered text and exit on key press"""
         hint = 'Press any key to continue'
         curses.cbreak()
@@ -1139,16 +1227,16 @@ class Tui(object):
                            curses.A_STANDOUT)
         self.screen.getkey()
 
-    def show_help_interactive(self):
+    def _show_help_interactive(self):
         """Display help with list of interactive commands"""
         msg = ('   b     toggle events by guests (debugfs only, honors'
                ' filters)',
                '   c     clear filter',
                '   f     filter by regular expression',
-               '   g     filter by guest name',
+               '   g     filter by guest name/PID',
                '   h     display interactive commands reference',
                '   o     toggle sorting order (Total vs CurAvg/s)',
-               '   p     filter by PID',
+               '   p     filter by guest name/PID',
                '   q     quit',
                '   r     reset stats',
                '   s     set update interval',
@@ -1165,14 +1253,15 @@ class Tui(object):
             self.screen.addstr(row, 0, line)
             row += 1
         self.screen.getkey()
-        self.refresh_header()
+        self._refresh_header()
 
-    def show_filter_selection(self):
+    def _show_filter_selection(self):
         """Draws filter selection mask.
 
         Asks for a valid regex and sets the fields filter accordingly.
 
         """
+        msg = ''
         while True:
             self.screen.erase()
             self.screen.addstr(0, 0,
@@ -1181,61 +1270,25 @@ class Tui(object):
             self.screen.addstr(2, 0,
                                "Current regex: {0}"
                                .format(self.stats.fields_filter))
+            self.screen.addstr(5, 0, msg)
             self.screen.addstr(3, 0, "New regex: ")
             curses.echo()
             regex = self.screen.getstr().decode(ENCODING)
             curses.noecho()
             if len(regex) == 0:
-                self.stats.fields_filter = DEFAULT_REGEX
-                self.refresh_header()
+                self.stats.fields_filter = ''
+                self._refresh_header()
                 return
             try:
                 re.compile(regex)
                 self.stats.fields_filter = regex
-                self.refresh_header()
+                self._refresh_header()
                 return
             except re.error:
+                msg = '"' + regex + '": Not a valid regular expression'
                 continue
 
-    def show_vm_selection_by_pid(self):
-        """Draws PID selection mask.
-
-        Asks for a pid until a valid pid or 0 has been entered.
-
-        """
-        msg = ''
-        while True:
-            self.screen.erase()
-            self.screen.addstr(0, 0,
-                               'Show statistics for specific pid.',
-                               curses.A_BOLD)
-            self.screen.addstr(1, 0,
-                               'This might limit the shown data to the trace '
-                               'statistics.')
-            self.screen.addstr(5, 0, msg)
-            self.print_all_gnames(7)
-
-            curses.echo()
-            self.screen.addstr(3, 0, "Pid [0 or pid]: ")
-            pid = self.screen.getstr().decode(ENCODING)
-            curses.noecho()
-
-            try:
-                if len(pid) > 0:
-                    pid = int(pid)
-                    if pid != 0 and not os.path.isdir(os.path.join('/proc/',
-                                                                   str(pid))):
-                        msg = '"' + str(pid) + '": Not a running process'
-                        continue
-                else:
-                    pid = 0
-                self.refresh_header(pid)
-                self.update_pid(pid)
-                break
-            except ValueError:
-                msg = '"' + str(pid) + '": Not a valid pid'
-
-    def show_set_update_interval(self):
+    def _show_set_update_interval(self):
         """Draws update interval selection mask."""
         msg = ''
         while True:
@@ -1265,60 +1318,67 @@ class Tui(object):
 
             except ValueError:
                 msg = '"' + str(val) + '": Invalid value'
-        self.refresh_header()
+        self._refresh_header()
 
-    def show_vm_selection_by_guest_name(self):
+    def _show_vm_selection_by_guest(self):
         """Draws guest selection mask.
 
-        Asks for a guest name until a valid guest name or '' is entered.
+        Asks for a guest name or pid until a valid guest name or '' is entered.
 
         """
         msg = ''
         while True:
             self.screen.erase()
             self.screen.addstr(0, 0,
-                               'Show statistics for specific guest.',
+                               'Show statistics for specific guest or pid.',
                                curses.A_BOLD)
             self.screen.addstr(1, 0,
                                'This might limit the shown data to the trace '
                                'statistics.')
             self.screen.addstr(5, 0, msg)
-            self.print_all_gnames(7)
+            self._print_all_gnames(7)
             curses.echo()
-            self.screen.addstr(3, 0, "Guest [ENTER or guest]: ")
-            gname = self.screen.getstr().decode(ENCODING)
+            curses.curs_set(1)
+            self.screen.addstr(3, 0, "Guest or pid [ENTER exits]: ")
+            guest = self.screen.getstr().decode(ENCODING)
             curses.noecho()
 
-            if not gname:
-                self.refresh_header(0)
-                self.update_pid(0)
+            pid = 0
+            if not guest or guest == '0':
                 break
-            else:
-                pids = []
-                try:
-                    pids = self.get_pid_from_gname(gname)
-                except:
-                    msg = '"' + gname + '": Internal error while searching, ' \
-                          'use pid filter instead'
-                    continue
-                if len(pids) == 0:
-                    msg = '"' + gname + '": Not an active guest'
+            if guest.isdigit():
+                if not os.path.isdir(os.path.join('/proc/', guest)):
+                    msg = '"' + guest + '": Not a running process'
                     continue
-                if len(pids) > 1:
-                    msg = '"' + gname + '": Multiple matches found, use pid ' \
-                          'filter instead'
-                    continue
-                self.refresh_header(pids[0])
-                self.update_pid(pids[0])
+                pid = int(guest)
                 break
+            pids = []
+            try:
+                pids = self.get_pid_from_gname(guest)
+            except:
+                msg = '"' + guest + '": Internal error while searching, ' \
+                      'use pid filter instead'
+                continue
+            if len(pids) == 0:
+                msg = '"' + guest + '": Not an active guest'
+                continue
+            if len(pids) > 1:
+                msg = '"' + guest + '": Multiple matches found, use pid ' \
+                      'filter instead'
+                continue
+            pid = pids[0]
+            break
+        curses.curs_set(0)
+        self._refresh_header(pid)
+        self._update_pid(pid)
 
     def show_stats(self):
         """Refreshes the screen and processes user input."""
         sleeptime = self._delay_initial
-        self.refresh_header()
+        self._refresh_header()
         start = 0.0  # result based on init value never appears on screen
         while True:
-            self.refresh_body(time.time() - start)
+            self._refresh_body(time.time() - start)
             curses.halfdelay(int(sleeptime * 10))
             start = time.time()
             sleeptime = self._delay_regular
@@ -1327,47 +1387,39 @@ class Tui(object):
                 if char == 'b':
                     self._display_guests = not self._display_guests
                     if self.stats.toggle_display_guests(self._display_guests):
-                        self.show_msg(['Command not available with tracepoints'
-                                       ' enabled', 'Restart with debugfs only '
-                                       '(see option \'-d\') and try again!'])
+                        self._show_msg(['Command not available with '
+                                        'tracepoints enabled', 'Restart with '
+                                        'debugfs only (see option \'-d\') and '
+                                        'try again!'])
                         self._display_guests = not self._display_guests
-                    self.refresh_header()
+                    self._refresh_header()
                 if char == 'c':
-                    self.stats.fields_filter = DEFAULT_REGEX
-                    self.refresh_header(0)
-                    self.update_pid(0)
+                    self.stats.fields_filter = ''
+                    self._refresh_header(0)
+                    self._update_pid(0)
                 if char == 'f':
                     curses.curs_set(1)
-                    self.show_filter_selection()
+                    self._show_filter_selection()
                     curses.curs_set(0)
                     sleeptime = self._delay_initial
-                if char == 'g':
-                    curses.curs_set(1)
-                    self.show_vm_selection_by_guest_name()
-                    curses.curs_set(0)
+                if char == 'g' or char == 'p':
+                    self._show_vm_selection_by_guest()
                     sleeptime = self._delay_initial
                 if char == 'h':
-                    self.show_help_interactive()
+                    self._show_help_interactive()
                 if char == 'o':
                     self._sorting = not self._sorting
-                if char == 'p':
-                    curses.curs_set(1)
-                    self.show_vm_selection_by_pid()
-                    curses.curs_set(0)
-                    sleeptime = self._delay_initial
                 if char == 'q':
                     break
                 if char == 'r':
                     self.stats.reset()
                 if char == 's':
                     curses.curs_set(1)
-                    self.show_set_update_interval()
+                    self._show_set_update_interval()
                     curses.curs_set(0)
                     sleeptime = self._delay_initial
                 if char == 'x':
-                    self.update_drilldown()
-                    # prevents display of current values on next refresh
-                    self.stats.get(self._display_guests)
+                    self.stats.child_events = not self.stats.child_events
             except KeyboardInterrupt:
                 break
             except curses.error:
@@ -1380,9 +1432,9 @@ def batch(stats):
         s = stats.get()
         time.sleep(1)
         s = stats.get()
-        for key in sorted(s.keys()):
-            values = s[key]
-            print('%-42s%10d%10d' % (key, values[0], values[1]))
+        for key, values in sorted(s.items()):
+            print('%-42s%10d%10d' % (key.split(' ')[0], values.value,
+                  values.delta))
     except KeyboardInterrupt:
         pass
 
@@ -1392,14 +1444,14 @@ def log(stats):
     keys = sorted(stats.get().keys())
 
     def banner():
-        for k in keys:
-            print(k, end=' ')
+        for key in keys:
+            print(key.split(' ')[0], end=' ')
         print()
 
     def statline():
         s = stats.get()
-        for k in keys:
-            print(' %9d' % s[k][1], end=' ')
+        for key in keys:
+            print(' %9d' % s[key].delta, end=' ')
         print()
     line = 0
     banner_repeat = 20
@@ -1504,7 +1556,7 @@ Press any other key to refresh statistics immediately.
                          )
     optparser.add_option('-f', '--fields',
                          action='store',
-                         default=DEFAULT_REGEX,
+                         default='',
                          dest='fields',
                          help='''fields to display (regex)
                                  "-f help" for a list of available events''',
@@ -1539,17 +1591,6 @@ Press any other key to refresh statistics immediately.
 
 def check_access(options):
     """Exits if the current user can't access all needed directories."""
-    if not os.path.exists('/sys/kernel/debug'):
-        sys.stderr.write('Please enable CONFIG_DEBUG_FS in your kernel.')
-        sys.exit(1)
-
-    if not os.path.exists(PATH_DEBUGFS_KVM):
-        sys.stderr.write("Please make sure, that debugfs is mounted and "
-                         "readable by the current user:\n"
-                         "('mount -t debugfs debugfs /sys/kernel/debug')\n"
-                         "Also ensure, that the kvm modules are loaded.\n")
-        sys.exit(1)
-
     if not os.path.exists(PATH_DEBUGFS_TRACING) and (options.tracepoints or
                                                      not options.debugfs):
         sys.stderr.write("Please enable CONFIG_TRACING in your kernel "
@@ -1567,7 +1608,33 @@ def check_access(options):
     return options
 
 
+def assign_globals():
+    global PATH_DEBUGFS_KVM
+    global PATH_DEBUGFS_TRACING
+
+    debugfs = ''
+    for line in file('/proc/mounts'):
+        if line.split(' ')[0] == 'debugfs':
+            debugfs = line.split(' ')[1]
+            break
+    if debugfs == '':
+        sys.stderr.write("Please make sure that CONFIG_DEBUG_FS is enabled in "
+                         "your kernel, mounted and\nreadable by the current "
+                         "user:\n"
+                         "('mount -t debugfs debugfs /sys/kernel/debug')\n")
+        sys.exit(1)
+
+    PATH_DEBUGFS_KVM = os.path.join(debugfs, 'kvm')
+    PATH_DEBUGFS_TRACING = os.path.join(debugfs, 'tracing')
+
+    if not os.path.exists(PATH_DEBUGFS_KVM):
+        sys.stderr.write("Please make sure that CONFIG_KVM is enabled in "
+                         "your kernel and that the modules are loaded.\n")
+        sys.exit(1)
+
+
 def main():
+    assign_globals()
     options = get_options()
     options = check_access(options)
 
diff --git a/tools/kvm/kvm_stat/kvm_stat.txt b/tools/kvm/kvm_stat/kvm_stat.txt
index b5b3810c9e94..0811d860fe75 100644
--- a/tools/kvm/kvm_stat/kvm_stat.txt
+++ b/tools/kvm/kvm_stat/kvm_stat.txt
@@ -35,13 +35,13 @@ INTERACTIVE COMMANDS
 
 *f*::   filter by regular expression
 
-*g*::   filter by guest name
+*g*::   filter by guest name/PID
 
 *h*::   display interactive commands reference
 
 *o*::   toggle sorting order (Total vs CurAvg/s)
 
-*p*::   filter by PID
+*p*::   filter by guest name/PID
 
 *q*::   quit
 
diff --git a/tools/laptop/freefall/Makefile b/tools/laptop/freefall/Makefile
index 5f758c489a20..b572d94255f6 100644
--- a/tools/laptop/freefall/Makefile
+++ b/tools/laptop/freefall/Makefile
@@ -2,7 +2,6 @@
 PREFIX ?= /usr
 SBINDIR ?= sbin
 INSTALL ?= install
-CC = $(CROSS_COMPILE)gcc
 
 TARGET = freefall
 
diff --git a/tools/leds/Makefile b/tools/leds/Makefile
index c379af003807..7b6bed13daaa 100644
--- a/tools/leds/Makefile
+++ b/tools/leds/Makefile
@@ -1,7 +1,6 @@
 # SPDX-License-Identifier: GPL-2.0
 # Makefile for LEDs tools
 
-CC = $(CROSS_COMPILE)gcc
 CFLAGS = -Wall -Wextra -g -I../../include/uapi
 
 all: uledmon led_hw_brightness_mon
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 97073d649c1a..5bbbf285af74 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -1060,11 +1060,12 @@ bpf_program__reloc_text(struct bpf_program *prog, struct bpf_object *obj,
                 prog->insns = new_insn;
                 prog->main_prog_cnt = prog->insns_cnt;
                 prog->insns_cnt = new_cnt;
+                pr_debug("added %zd insn from %s to prog %s\n",
+                         text->insns_cnt, text->section_name,
+                         prog->section_name);
         }
         insn = &prog->insns[relo->insn_idx];
         insn->imm += prog->main_prog_cnt - relo->insn_idx;
-        pr_debug("added %zd insn from %s to prog %s\n",
-                 text->insns_cnt, text->section_name, prog->section_name);
         return 0;
 }
 
diff --git a/tools/objtool/builtin-check.c b/tools/objtool/builtin-check.c
index 57254f5b2779..694abc628e9b 100644
--- a/tools/objtool/builtin-check.c
+++ b/tools/objtool/builtin-check.c
@@ -29,7 +29,7 @@
 #include "builtin.h"
 #include "check.h"
 
-bool no_fp, no_unreachable;
+bool no_fp, no_unreachable, retpoline, module;
 
 static const char * const check_usage[] = {
         "objtool check [<options>] file.o",
@@ -39,6 +39,8 @@ static const char * const check_usage[] = {
 const struct option check_options[] = {
         OPT_BOOLEAN('f', "no-fp", &no_fp, "Skip frame pointer validation"),
         OPT_BOOLEAN('u', "no-unreachable", &no_unreachable, "Skip 'unreachable instruction' warnings"),
+        OPT_BOOLEAN('r', "retpoline", &retpoline, "Validate retpoline assumptions"),
+        OPT_BOOLEAN('m', "module", &module, "Indicates the object will be part of a kernel module"),
         OPT_END(),
 };
 
@@ -53,5 +55,5 @@ int cmd_check(int argc, const char **argv)
 
         objname = argv[0];
 
-        return check(objname, no_fp, no_unreachable, false);
+        return check(objname, false);
 }
diff --git a/tools/objtool/builtin-orc.c b/tools/objtool/builtin-orc.c
index 91e8e19ff5e0..77ea2b97117d 100644
--- a/tools/objtool/builtin-orc.c
+++ b/tools/objtool/builtin-orc.c
@@ -25,7 +25,6 @@
  */
 
 #include <string.h>
-#include <subcmd/parse-options.h>
 #include "builtin.h"
 #include "check.h"
 
@@ -36,9 +35,6 @@ static const char *orc_usage[] = {
         NULL,
 };
 
-extern const struct option check_options[];
-extern bool no_fp, no_unreachable;
-
 int cmd_orc(int argc, const char **argv)
 {
         const char *objname;
@@ -54,7 +50,7 @@ int cmd_orc(int argc, const char **argv)
 
                 objname = argv[0];
 
-                return check(objname, no_fp, no_unreachable, true);
+                return check(objname, true);
         }
 
         if (!strcmp(argv[0], "dump")) {
diff --git a/tools/objtool/builtin.h b/tools/objtool/builtin.h
index dd526067fed5..28ff40e19a14 100644
--- a/tools/objtool/builtin.h
+++ b/tools/objtool/builtin.h
@@ -17,6 +17,11 @@
 #ifndef _BUILTIN_H
 #define _BUILTIN_H
 
+#include <subcmd/parse-options.h>
+
+extern const struct option check_options[];
+extern bool no_fp, no_unreachable, retpoline, module;
+
 extern int cmd_check(int argc, const char **argv);
 extern int cmd_orc(int argc, const char **argv);
 
diff --git a/tools/objtool/check.c b/tools/objtool/check.c
index b00b1896547e..92b6a2c21631 100644
--- a/tools/objtool/check.c
+++ b/tools/objtool/check.c
@@ -18,6 +18,7 @@
 #include <string.h>
 #include <stdlib.h>
 
+#include "builtin.h"
 #include "check.h"
 #include "elf.h"
 #include "special.h"
@@ -33,7 +34,6 @@ struct alternative {
 };
 
 const char *objname;
-static bool no_fp;
 struct cfi_state initial_func_cfi;
 
 struct instruction *find_insn(struct objtool_file *file,
@@ -497,6 +497,7 @@ static int add_jump_destinations(struct objtool_file *file)
                          * disguise, so convert them accordingly.
                          */
                         insn->type = INSN_JUMP_DYNAMIC;
+                        insn->retpoline_safe = true;
                         continue;
                 } else {
                         /* sibling call */
@@ -548,7 +549,8 @@ static int add_call_destinations(struct objtool_file *file)
                         if (!insn->call_dest && !insn->ignore) {
                                 WARN_FUNC("unsupported intra-function call",
                                           insn->sec, insn->offset);
-                                WARN("If this is a retpoline, please patch it in with alternatives and annotate it with ANNOTATE_NOSPEC_ALTERNATIVE.");
+                                if (retpoline)
+                                        WARN("If this is a retpoline, please patch it in with alternatives and annotate it with ANNOTATE_NOSPEC_ALTERNATIVE.");
                                 return -1;
                         }
 
@@ -852,8 +854,14 @@ static int add_switch_table(struct objtool_file *file, struct symbol *func,
  *    This is a fairly uncommon pattern which is new for GCC 6.  As of this
  *    writing, there are 11 occurrences of it in the allmodconfig kernel.
  *
+ *    As of GCC 7 there are quite a few more of these and the 'in between' code
+ *    is significant. Esp. with KASAN enabled some of the code between the mov
+ *    and jmpq uses .rodata itself, which can confuse things.
+ *
  *    TODO: Once we have DWARF CFI and smarter instruction decoding logic,
  *    ensure the same register is used in the mov and jump instructions.
+ *
+ *    NOTE: RETPOLINE made it harder still to decode dynamic jumps.
  */
 static struct rela *find_switch_table(struct objtool_file *file,
                                       struct symbol *func,
@@ -875,12 +883,25 @@ static struct rela *find_switch_table(struct objtool_file *file,
                                                 text_rela->addend + 4);
                 if (!rodata_rela)
                         return NULL;
+
                 file->ignore_unreachables = true;
                 return rodata_rela;
         }
 
         /* case 3 */
-        func_for_each_insn_continue_reverse(file, func, insn) {
+        /*
+         * Backward search using the @first_jump_src links, these help avoid
+         * much of the 'in between' code. Which avoids us getting confused by
+         * it.
+         */
+        for (insn = list_prev_entry(insn, list);
+
+             &insn->list != &file->insn_list &&
+             insn->sec == func->sec &&
+             insn->offset >= func->offset;
+
+             insn = insn->first_jump_src ?: list_prev_entry(insn, list)) {
+
                 if (insn->type == INSN_JUMP_DYNAMIC)
                         break;
 
@@ -904,20 +925,42 @@ static struct rela *find_switch_table(struct objtool_file *file,
                 if (find_symbol_containing(file->rodata, text_rela->addend))
                         continue;
 
-                return find_rela_by_dest(file->rodata, text_rela->addend);
+                rodata_rela = find_rela_by_dest(file->rodata, text_rela->addend);
+                if (!rodata_rela)
+                        continue;
+
+                return rodata_rela;
         }
 
         return NULL;
 }
 
+
 static int add_func_switch_tables(struct objtool_file *file,
                                   struct symbol *func)
 {
-        struct instruction *insn, *prev_jump = NULL;
+        struct instruction *insn, *last = NULL, *prev_jump = NULL;
         struct rela *rela, *prev_rela = NULL;
         int ret;
 
         func_for_each_insn(file, func, insn) {
+                if (!last)
+                        last = insn;
+
+                /*
+                 * Store back-pointers for unconditional forward jumps such
+                 * that find_switch_table() can back-track using those and
+                 * avoid some potentially confusing code.
+                 */
+                if (insn->type == INSN_JUMP_UNCONDITIONAL && insn->jump_dest &&
+                    insn->offset > last->offset &&
+                    insn->jump_dest->offset > insn->offset &&
+                    !insn->jump_dest->first_jump_src) {
+
+                        insn->jump_dest->first_jump_src = insn;
+                        last = insn->jump_dest;
+                }
+
                 if (insn->type != INSN_JUMP_DYNAMIC)
                         continue;
 
@@ -1071,6 +1114,41 @@ static int read_unwind_hints(struct objtool_file *file)
         return 0;
 }
 
+static int read_retpoline_hints(struct objtool_file *file)
+{
+        struct section *sec;
+        struct instruction *insn;
+        struct rela *rela;
+
+        sec = find_section_by_name(file->elf, ".rela.discard.retpoline_safe");
+        if (!sec)
+                return 0;
+
+        list_for_each_entry(rela, &sec->rela_list, list) {
+                if (rela->sym->type != STT_SECTION) {
+                        WARN("unexpected relocation symbol type in %s", sec->name);
+                        return -1;
+                }
+
+                insn = find_insn(file, rela->sym->sec, rela->addend);
+                if (!insn) {
+                        WARN("bad .discard.retpoline_safe entry");
+                        return -1;
+                }
+
+                if (insn->type != INSN_JUMP_DYNAMIC &&
+                    insn->type != INSN_CALL_DYNAMIC) {
+                        WARN_FUNC("retpoline_safe hint not an indirect jump/call",
+                                  insn->sec, insn->offset);
+                        return -1;
+                }
+
+                insn->retpoline_safe = true;
+        }
+
+        return 0;
+}
+
 static int decode_sections(struct objtool_file *file)
 {
         int ret;
@@ -1109,6 +1187,10 @@ static int decode_sections(struct objtool_file *file)
         if (ret)
                 return ret;
 
+        ret = read_retpoline_hints(file);
+        if (ret)
+                return ret;
+
         return 0;
 }
 
@@ -1854,6 +1936,38 @@ static int validate_unwind_hints(struct objtool_file *file)
         return warnings;
 }
 
+static int validate_retpoline(struct objtool_file *file)
+{
+        struct instruction *insn;
+        int warnings = 0;
+
+        for_each_insn(file, insn) {
+                if (insn->type != INSN_JUMP_DYNAMIC &&
+                    insn->type != INSN_CALL_DYNAMIC)
+                        continue;
+
+                if (insn->retpoline_safe)
+                        continue;
+
+                /*
+                 * .init.text code is ran before userspace and thus doesn't
+                 * strictly need retpolines, except for modules which are
+                 * loaded late, they very much do need retpoline in their
+                 * .init.text
+                 */
+                if (!strcmp(insn->sec->name, ".init.text") && !module)
+                        continue;
+
+                WARN_FUNC("indirect %s found in RETPOLINE build",
+                          insn->sec, insn->offset,
+                          insn->type == INSN_JUMP_DYNAMIC ? "jump" : "call");
+
+                warnings++;
+        }
+
+        return warnings;
+}
+
 static bool is_kasan_insn(struct instruction *insn)
 {
         return (insn->type == INSN_CALL &&
@@ -1899,13 +2013,19 @@ static bool ignore_unreachable_insn(struct instruction *insn)
                 if (is_kasan_insn(insn) || is_ubsan_insn(insn))
                         return true;
 
-                if (insn->type == INSN_JUMP_UNCONDITIONAL && insn->jump_dest) {
-                        insn = insn->jump_dest;
-                        continue;
+                if (insn->type == INSN_JUMP_UNCONDITIONAL) {
+                        if (insn->jump_dest &&
+                            insn->jump_dest->func == insn->func) {
+                                insn = insn->jump_dest;
+                                continue;
+                        }
+
+                        break;
                 }
 
                 if (insn->offset + insn->len >= insn->func->offset + insn->func->len)
                         break;
+
                 insn = list_next_entry(insn, list);
         }
 
@@ -1979,13 +2099,12 @@ static void cleanup(struct objtool_file *file)
         elf_close(file->elf);
 }
 
-int check(const char *_objname, bool _no_fp, bool no_unreachable, bool orc)
+int check(const char *_objname, bool orc)
 {
         struct objtool_file file;
         int ret, warnings = 0;
 
         objname = _objname;
-        no_fp = _no_fp;
 
         file.elf = elf_open(objname, orc ? O_RDWR : O_RDONLY);
         if (!file.elf)
@@ -2009,6 +2128,13 @@ int check(const char *_objname, bool _no_fp, bool no_unreachable, bool orc)
         if (list_empty(&file.insn_list))
                 goto out;
 
+        if (retpoline) {
+                ret = validate_retpoline(&file);
+                if (ret < 0)
+                        return ret;
+                warnings += ret;
+        }
+
         ret = validate_functions(&file);
         if (ret < 0)
                 goto out;
diff --git a/tools/objtool/check.h b/tools/objtool/check.h
index dbadb304a410..c6b68fcb926f 100644
--- a/tools/objtool/check.h
+++ b/tools/objtool/check.h
@@ -45,8 +45,10 @@ struct instruction {
         unsigned char type;
         unsigned long immediate;
         bool alt_group, visited, dead_end, ignore, hint, save, restore, ignore_alts;
+        bool retpoline_safe;
         struct symbol *call_dest;
         struct instruction *jump_dest;
+        struct instruction *first_jump_src;
         struct list_head alts;
         struct symbol *func;
         struct stack_op stack_op;
@@ -62,7 +64,7 @@ struct objtool_file {
         bool ignore_unreachables, c_file, hints;
 };
 
-int check(const char *objname, bool no_fp, bool no_unreachable, bool orc);
+int check(const char *objname, bool orc);
 
 struct instruction *find_insn(struct objtool_file *file,
                               struct section *sec, unsigned long offset);
diff --git a/tools/perf/Documentation/perf-data.txt b/tools/perf/Documentation/perf-data.txt
index f0796a47dfa3..90bb4aabe4f8 100644
--- a/tools/perf/Documentation/perf-data.txt
+++ b/tools/perf/Documentation/perf-data.txt
@@ -30,6 +30,10 @@ OPTIONS for 'convert'
 -i::
         Specify input perf data file path.
 
+-f::
+--force::
+        Don't complain, do it.
+
 -v::
 --verbose::
         Be more verbose (show counter open errors, etc).
diff --git a/tools/perf/Documentation/perf-kallsyms.txt b/tools/perf/Documentation/perf-kallsyms.txt
index 954ea9e21236..cf9f4040ea5c 100644
--- a/tools/perf/Documentation/perf-kallsyms.txt
+++ b/tools/perf/Documentation/perf-kallsyms.txt
@@ -8,7 +8,7 @@ perf-kallsyms - Searches running kernel for symbols
 SYNOPSIS
 --------
 [verse]
-'perf kallsyms <options> symbol_name[,symbol_name...]'
+'perf kallsyms' [<options>] symbol_name[,symbol_name...]
 
 DESCRIPTION
 -----------
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index 9b0351d3ce34..012328038594 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -146,12 +146,6 @@ define allow-override
     $(eval $(1) = $(2)))
 endef
 
-# Allow setting CC and AR and LD, or setting CROSS_COMPILE as a prefix.
-$(call allow-override,CC,$(CROSS_COMPILE)gcc)
-$(call allow-override,AR,$(CROSS_COMPILE)ar)
-$(call allow-override,LD,$(CROSS_COMPILE)ld)
-$(call allow-override,CXX,$(CROSS_COMPILE)g++)
-
 LD += $(EXTRA_LDFLAGS)
 
 HOSTCC  ?= gcc
diff --git a/tools/perf/arch/s390/Makefile b/tools/perf/arch/s390/Makefile
index 48228de415d0..dfa6e3103437 100644
--- a/tools/perf/arch/s390/Makefile
+++ b/tools/perf/arch/s390/Makefile
@@ -10,15 +10,19 @@ PERF_HAVE_ARCH_REGS_QUERY_REGISTER_OFFSET := 1
 
 out    := $(OUTPUT)arch/s390/include/generated/asm
 header := $(out)/syscalls_64.c
-sysdef := $(srctree)/tools/arch/s390/include/uapi/asm/unistd.h
-sysprf := $(srctree)/tools/perf/arch/s390/entry/syscalls/
+syskrn := $(srctree)/arch/s390/kernel/syscalls/syscall.tbl
+sysprf := $(srctree)/tools/perf/arch/s390/entry/syscalls
+sysdef := $(sysprf)/syscall.tbl
 systbl := $(sysprf)/mksyscalltbl
 
 # Create output directory if not already present
 _dummy := $(shell [ -d '$(out)' ] || mkdir -p '$(out)')
 
 $(header): $(sysdef) $(systbl)
-        $(Q)$(SHELL) '$(systbl)' '$(CC)' $(sysdef) > $@
+        @(test -d ../../kernel -a -d ../../tools -a -d ../perf && ( \
+        (diff -B $(sysdef) $(syskrn) >/dev/null) \
+        || echo "Warning: Kernel ABI header at '$(sysdef)' differs from latest version at '$(syskrn)'" >&2 )) || true
+        $(Q)$(SHELL) '$(systbl)' $(sysdef) > $@
 
 clean::
         $(call QUIET_CLEAN, s390) $(RM) $(header)
diff --git a/tools/perf/arch/s390/entry/syscalls/mksyscalltbl b/tools/perf/arch/s390/entry/syscalls/mksyscalltbl
index 7fa0d0abd419..72ecbb676370 100755
--- a/tools/perf/arch/s390/entry/syscalls/mksyscalltbl
+++ b/tools/perf/arch/s390/entry/syscalls/mksyscalltbl
@@ -3,25 +3,23 @@
 #
 # Generate system call table for perf
 #
-#
-# Copyright IBM Corp. 2017
+# Copyright IBM Corp. 2017, 2018
 # Author(s):  Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
 #
 
-gcc=$1
-input=$2
+SYSCALL_TBL=$1
 
-if ! test -r $input; then
+if ! test -r $SYSCALL_TBL; then
         echo "Could not read input file" >&2
         exit 1
 fi
 
 create_table()
 {
-        local max_nr
+        local max_nr nr abi sc discard
 
         echo 'static const char *syscalltbl_s390_64[] = {'
-        while read sc nr; do
+        while read nr abi sc discard; do
                 printf '\t[%d] = "%s",\n' $nr $sc
                 max_nr=$nr
         done
@@ -29,8 +27,6 @@ create_table()
         echo "#define SYSCALLTBL_S390_64_MAX_ID $max_nr"
 }
 
-
-$gcc -m64 -E -dM -x c  $input          \
-        |sed -ne 's/^#define __NR_//p' \
-        |sort -t' ' -k2 -nu            \
+grep -E "^[[:digit:]]+[[:space:]]+(common|64)" $SYSCALL_TBL     \
+        |sort -k1 -n                                    \
         |create_table
diff --git a/tools/perf/arch/s390/entry/syscalls/syscall.tbl b/tools/perf/arch/s390/entry/syscalls/syscall.tbl
new file mode 100644
index 000000000000..b38d48464368
--- /dev/null
+++ b/tools/perf/arch/s390/entry/syscalls/syscall.tbl
@@ -0,0 +1,390 @@
+# SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note
+#
+# System call table for s390
+#
+# Format:
+#
+# <nr> <abi> <syscall> <entry-64bit> <compat-entry>
+#
+# where <abi> can be common, 64, or 32
+
+1    common     exit                    sys_exit                        sys_exit
+2    common     fork                    sys_fork                        sys_fork
+3    common     read                    sys_read                        compat_sys_s390_read
+4    common     write                   sys_write                       compat_sys_s390_write
+5    common     open                    sys_open                        compat_sys_open
+6    common     close                   sys_close                       sys_close
+7    common     restart_syscall         sys_restart_syscall             sys_restart_syscall
+8    common     creat                   sys_creat                       compat_sys_creat
+9    common     link                    sys_link                        compat_sys_link
+10   common     unlink                  sys_unlink                      compat_sys_unlink
+11   common     execve                  sys_execve                      compat_sys_execve
+12   common     chdir                   sys_chdir                       compat_sys_chdir
+13   32         time                    -                               compat_sys_time
+14   common     mknod                   sys_mknod                       compat_sys_mknod
+15   common     chmod                   sys_chmod                       compat_sys_chmod
+16   32         lchown                  -                               compat_sys_s390_lchown16
+19   common     lseek                   sys_lseek                       compat_sys_lseek
+20   common     getpid                  sys_getpid                      sys_getpid
+21   common     mount                   sys_mount                       compat_sys_mount
+22   common     umount                  sys_oldumount                   compat_sys_oldumount
+23   32         setuid                  -                               compat_sys_s390_setuid16
+24   32         getuid                  -                               compat_sys_s390_getuid16
+25   32         stime                   -                               compat_sys_stime
+26   common     ptrace                  sys_ptrace                      compat_sys_ptrace
+27   common     alarm                   sys_alarm                       sys_alarm
+29   common     pause                   sys_pause                       sys_pause
+30   common     utime                   sys_utime                       compat_sys_utime
+33   common     access                  sys_access                      compat_sys_access
+34   common     nice                    sys_nice                        sys_nice
+36   common     sync                    sys_sync                        sys_sync
+37   common     kill                    sys_kill                        sys_kill
+38   common     rename                  sys_rename                      compat_sys_rename
+39   common     mkdir                   sys_mkdir                       compat_sys_mkdir
+40   common     rmdir                   sys_rmdir                       compat_sys_rmdir
+41   common     dup                     sys_dup                         sys_dup
+42   common     pipe                    sys_pipe                        compat_sys_pipe
+43   common     times                   sys_times                       compat_sys_times
+45   common     brk                     sys_brk                         compat_sys_brk
+46   32         setgid                  -                               compat_sys_s390_setgid16
+47   32         getgid                  -                               compat_sys_s390_getgid16
+48   common     signal                  sys_signal                      compat_sys_signal
+49   32         geteuid                 -                               compat_sys_s390_geteuid16
+50   32         getegid                 -                               compat_sys_s390_getegid16
+51   common     acct                    sys_acct                        compat_sys_acct
+52   common     umount2                 sys_umount                      compat_sys_umount
+54   common     ioctl                   sys_ioctl                       compat_sys_ioctl
+55   common     fcntl                   sys_fcntl                       compat_sys_fcntl
+57   common     setpgid                 sys_setpgid                     sys_setpgid
+60   common     umask                   sys_umask                       sys_umask
+61   common     chroot                  sys_chroot                      compat_sys_chroot
+62   common     ustat                   sys_ustat                       compat_sys_ustat
+63   common     dup2                    sys_dup2                        sys_dup2
+64   common     getppid                 sys_getppid                     sys_getppid
+65   common     getpgrp                 sys_getpgrp                     sys_getpgrp
+66   common     setsid                  sys_setsid                      sys_setsid
+67   common     sigaction               sys_sigaction                   compat_sys_sigaction
+70   32         setreuid                -                               compat_sys_s390_setreuid16
+71   32         setregid                -                               compat_sys_s390_setregid16
+72   common     sigsuspend              sys_sigsuspend                  compat_sys_sigsuspend
+73   common     sigpending              sys_sigpending                  compat_sys_sigpending
+74   common     sethostname             sys_sethostname                 compat_sys_sethostname
+75   common     setrlimit               sys_setrlimit                   compat_sys_setrlimit
+76   32         getrlimit               -                               compat_sys_old_getrlimit
+77   common     getrusage               sys_getrusage                   compat_sys_getrusage
+78   common     gettimeofday            sys_gettimeofday                compat_sys_gettimeofday
+79   common     settimeofday            sys_settimeofday                compat_sys_settimeofday
+80   32         getgroups               -                               compat_sys_s390_getgroups16
+81   32         setgroups               -                               compat_sys_s390_setgroups16
+83   common     symlink                 sys_symlink                     compat_sys_symlink
+85   common     readlink                sys_readlink                    compat_sys_readlink
+86   common     uselib                  sys_uselib                      compat_sys_uselib
+87   common     swapon                  sys_swapon                      compat_sys_swapon
+88   common     reboot                  sys_reboot                      compat_sys_reboot
+89   common     readdir                 -                               compat_sys_old_readdir
+90   common     mmap                    sys_old_mmap                    compat_sys_s390_old_mmap
+91   common     munmap                  sys_munmap                      compat_sys_munmap
+92   common     truncate                sys_truncate                    compat_sys_truncate
+93   common     ftruncate               sys_ftruncate                   compat_sys_ftruncate
+94   common     fchmod                  sys_fchmod                      sys_fchmod
+95   32         fchown                  -                               compat_sys_s390_fchown16
+96   common     getpriority             sys_getpriority                 sys_getpriority
+97   common     setpriority             sys_setpriority                 sys_setpriority
+99   common     statfs                  sys_statfs                      compat_sys_statfs
+100  common     fstatfs                 sys_fstatfs                     compat_sys_fstatfs
+101  32         ioperm                  -                               -
+102  common     socketcall              sys_socketcall                  compat_sys_socketcall
+103  common     syslog                  sys_syslog                      compat_sys_syslog
+104  common     setitimer               sys_setitimer                   compat_sys_setitimer
+105  common     getitimer               sys_getitimer                   compat_sys_getitimer
+106  common     stat                    sys_newstat                     compat_sys_newstat
+107  common     lstat                   sys_newlstat                    compat_sys_newlstat
+108  common     fstat                   sys_newfstat                    compat_sys_newfstat
+110  common     lookup_dcookie          sys_lookup_dcookie              compat_sys_lookup_dcookie
+111  common     vhangup                 sys_vhangup                     sys_vhangup
+112  common     idle                    -                               -
+114  common     wait4                   sys_wait4                       compat_sys_wait4
+115  common     swapoff                 sys_swapoff                     compat_sys_swapoff
+116  common     sysinfo                 sys_sysinfo                     compat_sys_sysinfo
+117  common     ipc                     sys_s390_ipc                    compat_sys_s390_ipc
+118  common     fsync                   sys_fsync                       sys_fsync
+119  common     sigreturn               sys_sigreturn                   compat_sys_sigreturn
+120  common     clone                   sys_clone                       compat_sys_clone
+121  common     setdomainname           sys_setdomainname               compat_sys_setdomainname
+122  common     uname                   sys_newuname                    compat_sys_newuname
+124  common     adjtimex                sys_adjtimex                    compat_sys_adjtimex
+125  common     mprotect                sys_mprotect                    compat_sys_mprotect
+126  common     sigprocmask             sys_sigprocmask                 compat_sys_sigprocmask
+127  common     create_module           -                               -
+128  common     init_module             sys_init_module                 compat_sys_init_module
+129  common     delete_module           sys_delete_module               compat_sys_delete_module
+130  common     get_kernel_syms         -                               -
+131  common     quotactl                sys_quotactl                    compat_sys_quotactl
+132  common     getpgid                 sys_getpgid                     sys_getpgid
+133  common     fchdir                  sys_fchdir                      sys_fchdir
+134  common     bdflush                 sys_bdflush                     compat_sys_bdflush
+135  common     sysfs                   sys_sysfs                       compat_sys_sysfs
+136  common     personality             sys_s390_personality            sys_s390_personality
+137  common     afs_syscall             -                               -
+138  32         setfsuid                -                               compat_sys_s390_setfsuid16
+139  32         setfsgid                -                               compat_sys_s390_setfsgid16
+140  32         _llseek                 -                               compat_sys_llseek
+141  common     getdents                sys_getdents                    compat_sys_getdents
+142  32         _newselect              -                               compat_sys_select
+142  64         select                  sys_select                      -
+143  common     flock                   sys_flock                       sys_flock
+144  common     msync                   sys_msync                       compat_sys_msync
+145  common     readv                   sys_readv                       compat_sys_readv
+146  common     writev                  sys_writev                      compat_sys_writev
+147  common     getsid                  sys_getsid                      sys_getsid
+148  common     fdatasync               sys_fdatasync                   sys_fdatasync
+149  common     _sysctl                 sys_sysctl                      compat_sys_sysctl
+150  common     mlock                   sys_mlock                       compat_sys_mlock
+151  common     munlock                 sys_munlock                     compat_sys_munlock
+152  common     mlockall                sys_mlockall                    sys_mlockall
+153  common     munlockall              sys_munlockall                  sys_munlockall
+154  common     sched_setparam          sys_sched_setparam              compat_sys_sched_setparam
+155  common     sched_getparam          sys_sched_getparam              compat_sys_sched_getparam
+156  common     sched_setscheduler      sys_sched_setscheduler          compat_sys_sched_setscheduler
+157  common     sched_getscheduler      sys_sched_getscheduler          sys_sched_getscheduler
+158  common     sched_yield             sys_sched_yield                 sys_sched_yield
+159  common     sched_get_priority_max  sys_sched_get_priority_max      sys_sched_get_priority_max
+160  common     sched_get_priority_min  sys_sched_get_priority_min      sys_sched_get_priority_min
+161  common     sched_rr_get_interval   sys_sched_rr_get_interval       compat_sys_sched_rr_get_interval
+162  common     nanosleep               sys_nanosleep                   compat_sys_nanosleep
+163  common     mremap                  sys_mremap                      compat_sys_mremap
+164  32         setresuid               -                               compat_sys_s390_setresuid16
+165  32         getresuid               -                               compat_sys_s390_getresuid16
+167  common     query_module            -                               -
+168  common     poll                    sys_poll                        compat_sys_poll
+169  common     nfsservctl              -                               -
+170  32         setresgid               -                               compat_sys_s390_setresgid16
+171  32         getresgid               -                               compat_sys_s390_getresgid16
+172  common     prctl                   sys_prctl                       compat_sys_prctl
+173  common     rt_sigreturn            sys_rt_sigreturn                compat_sys_rt_sigreturn
+174  common     rt_sigaction            sys_rt_sigaction                compat_sys_rt_sigaction
+175  common     rt_sigprocmask          sys_rt_sigprocmask              compat_sys_rt_sigprocmask
+176  common     rt_sigpending           sys_rt_sigpending               compat_sys_rt_sigpending
+177  common     rt_sigtimedwait         sys_rt_sigtimedwait             compat_sys_rt_sigtimedwait
+178  common     rt_sigqueueinfo         sys_rt_sigqueueinfo             compat_sys_rt_sigqueueinfo
+179  common     rt_sigsuspend           sys_rt_sigsuspend               compat_sys_rt_sigsuspend
+180  common     pread64                 sys_pread64                     compat_sys_s390_pread64
+181  common     pwrite64                sys_pwrite64                    compat_sys_s390_pwrite64
+182  32         chown                   -                               compat_sys_s390_chown16
+183  common     getcwd                  sys_getcwd                      compat_sys_getcwd
+184  common     capget                  sys_capget                      compat_sys_capget
+185  common     capset                  sys_capset                      compat_sys_capset
+186  common     sigaltstack             sys_sigaltstack                 compat_sys_sigaltstack
+187  common     sendfile                sys_sendfile64                  compat_sys_sendfile
+188  common     getpmsg                 -                               -
+189  common     putpmsg                 -                               -
+190  common     vfork                   sys_vfork                       sys_vfork
+191  32         ugetrlimit              -                               compat_sys_getrlimit
+191  64         getrlimit               sys_getrlimit                   -
+192  32         mmap2                   -                               compat_sys_s390_mmap2
+193  32         truncate64              -                               compat_sys_s390_truncate64
+194  32         ftruncate64             -                               compat_sys_s390_ftruncate64
+195  32         stat64                  -                               compat_sys_s390_stat64
+196  32         lstat64                 -                               compat_sys_s390_lstat64
+197  32         fstat64                 -                               compat_sys_s390_fstat64
+198  32         lchown32                -                               compat_sys_lchown
+198  64         lchown                  sys_lchown                      -
+199  32         getuid32                -                               sys_getuid
+199  64         getuid                  sys_getuid                      -
+200  32         getgid32                -                               sys_getgid
+200  64         getgid                  sys_getgid                      -
+201  32         geteuid32               -                               sys_geteuid
+201  64         geteuid                 sys_geteuid                     -
+202  32         getegid32               -                               sys_getegid
+202  64         getegid                 sys_getegid                     -
+203  32         setreuid32              -                               sys_setreuid
+203  64         setreuid                sys_setreuid                    -
+204  32         setregid32              -                               sys_setregid
+204  64         setregid                sys_setregid                    -
+205  32         getgroups32             -                               compat_sys_getgroups
+205  64         getgroups               sys_getgroups                   -
+206  32         setgroups32             -                               compat_sys_setgroups
+206  64         setgroups               sys_setgroups                   -
+207  32         fchown32                -                               sys_fchown
+207  64         fchown                  sys_fchown                      -
+208  32         setresuid32             -                               sys_setresuid
+208  64         setresuid               sys_setresuid                   -
+209  32         getresuid32             -                               compat_sys_getresuid
+209  64         getresuid               sys_getresuid                   -
+210  32         setresgid32             -                               sys_setresgid
+210  64         setresgid               sys_setresgid                   -
+211  32         getresgid32             -                               compat_sys_getresgid
+211  64         getresgid               sys_getresgid                   -
+212  32         chown32                 -                               compat_sys_chown
+212  64         chown                   sys_chown                       -
+213  32         setuid32                -                               sys_setuid
+213  64         setuid                  sys_setuid                      -
+214  32         setgid32                -                               sys_setgid
+214  64         setgid                  sys_setgid                      -
+215  32         setfsuid32              -                               sys_setfsuid
+215  64         setfsuid                sys_setfsuid                    -
+216  32         setfsgid32              -                               sys_setfsgid
+216  64         setfsgid                sys_setfsgid                    -
+217  common     pivot_root              sys_pivot_root                  compat_sys_pivot_root
+218  common     mincore                 sys_mincore                     compat_sys_mincore
+219  common     madvise                 sys_madvise                     compat_sys_madvise
+220  common     getdents64              sys_getdents64                  compat_sys_getdents64
+221  32         fcntl64                 -                               compat_sys_fcntl64
+222  common     readahead               sys_readahead                   compat_sys_s390_readahead
+223  32         sendfile64              -                               compat_sys_sendfile64
+224  common     setxattr                sys_setxattr                    compat_sys_setxattr
+225  common     lsetxattr               sys_lsetxattr                   compat_sys_lsetxattr
+226  common     fsetxattr               sys_fsetxattr                   compat_sys_fsetxattr
+227  common     getxattr                sys_getxattr                    compat_sys_getxattr
+228  common     lgetxattr               sys_lgetxattr                   compat_sys_lgetxattr
+229  common     fgetxattr               sys_fgetxattr                   compat_sys_fgetxattr
+230  common     listxattr               sys_listxattr                   compat_sys_listxattr
+231  common     llistxattr              sys_llistxattr                  compat_sys_llistxattr
+232  common     flistxattr              sys_flistxattr                  compat_sys_flistxattr
+233  common     removexattr             sys_removexattr                 compat_sys_removexattr
+234  common     lremovexattr            sys_lremovexattr                compat_sys_lremovexattr
+235  common     fremovexattr            sys_fremovexattr                compat_sys_fremovexattr
+236  common     gettid                  sys_gettid                      sys_gettid
+237  common     tkill                   sys_tkill                       sys_tkill
+238  common     futex                   sys_futex                       compat_sys_futex
+239  common     sched_setaffinity       sys_sched_setaffinity           compat_sys_sched_setaffinity
+240  common     sched_getaffinity       sys_sched_getaffinity           compat_sys_sched_getaffinity
+241  common     tgkill                  sys_tgkill                      sys_tgkill
+243  common     io_setup                sys_io_setup                    compat_sys_io_setup
+244  common     io_destroy              sys_io_destroy                  compat_sys_io_destroy
+245  common     io_getevents            sys_io_getevents                compat_sys_io_getevents
+246  common     io_submit               sys_io_submit                   compat_sys_io_submit
+247  common     io_cancel               sys_io_cancel                   compat_sys_io_cancel
+248  common     exit_group              sys_exit_group                  sys_exit_group
+249  common     epoll_create            sys_epoll_create                sys_epoll_create
+250  common     epoll_ctl               sys_epoll_ctl                   compat_sys_epoll_ctl
+251  common     epoll_wait              sys_epoll_wait                  compat_sys_epoll_wait
+252  common     set_tid_address         sys_set_tid_address             compat_sys_set_tid_address
+253  common     fadvise64               sys_fadvise64_64                compat_sys_s390_fadvise64
+254  common     timer_create            sys_timer_create                compat_sys_timer_create
+255  common     timer_settime           sys_timer_settime               compat_sys_timer_settime
+256  common     timer_gettime           sys_timer_gettime               compat_sys_timer_gettime
+257  common     timer_getoverrun        sys_timer_getoverrun            sys_timer_getoverrun
+258  common     timer_delete            sys_timer_delete                sys_timer_delete
+259  common     clock_settime           sys_clock_settime               compat_sys_clock_settime
+260  common     clock_gettime           sys_clock_gettime               compat_sys_clock_gettime
+261  common     clock_getres            sys_clock_getres                compat_sys_clock_getres
+262  common     clock_nanosleep         sys_clock_nanosleep             compat_sys_clock_nanosleep
+264  32         fadvise64_64            -                               compat_sys_s390_fadvise64_64
+265  common     statfs64                sys_statfs64                    compat_sys_statfs64
+266  common     fstatfs64               sys_fstatfs64                   compat_sys_fstatfs64
+267  common     remap_file_pages        sys_remap_file_pages            compat_sys_remap_file_pages
+268  common     mbind                   sys_mbind                       compat_sys_mbind
+269  common     get_mempolicy           sys_get_mempolicy               compat_sys_get_mempolicy
+270  common     set_mempolicy           sys_set_mempolicy               compat_sys_set_mempolicy
+271  common     mq_open                 sys_mq_open                     compat_sys_mq_open
+272  common     mq_unlink               sys_mq_unlink                   compat_sys_mq_unlink
+273  common     mq_timedsend            sys_mq_timedsend                compat_sys_mq_timedsend
+274  common     mq_timedreceive         sys_mq_timedreceive             compat_sys_mq_timedreceive
+275  common     mq_notify               sys_mq_notify                   compat_sys_mq_notify
+276  common     mq_getsetattr           sys_mq_getsetattr               compat_sys_mq_getsetattr
+277  common     kexec_load              sys_kexec_load                  compat_sys_kexec_load
+278  common     add_key                 sys_add_key                     compat_sys_add_key
+279  common     request_key             sys_request_key                 compat_sys_request_key
+280  common     keyctl                  sys_keyctl                      compat_sys_keyctl
+281  common     waitid                  sys_waitid                      compat_sys_waitid
+282  common     ioprio_set              sys_ioprio_set                  sys_ioprio_set
+283  common     ioprio_get              sys_ioprio_get                  sys_ioprio_get
+284  common     inotify_init            sys_inotify_init                sys_inotify_init
+285  common     inotify_add_watch       sys_inotify_add_watch           compat_sys_inotify_add_watch
+286  common     inotify_rm_watch        sys_inotify_rm_watch            sys_inotify_rm_watch
+287  common     migrate_pages           sys_migrate_pages               compat_sys_migrate_pages
+288  common     openat                  sys_openat                      compat_sys_openat
+289  common     mkdirat                 sys_mkdirat                     compat_sys_mkdirat
+290  common     mknodat                 sys_mknodat                     compat_sys_mknodat
+291  common     fchownat                sys_fchownat                    compat_sys_fchownat
+292  common     futimesat               sys_futimesat                   compat_sys_futimesat
+293  32         fstatat64               -                               compat_sys_s390_fstatat64
+293  64         newfstatat              sys_newfstatat                  -
+294  common     unlinkat                sys_unlinkat                    compat_sys_unlinkat
+295  common     renameat                sys_renameat                    compat_sys_renameat
+296  common     linkat                  sys_linkat                      compat_sys_linkat
+297  common     symlinkat               sys_symlinkat                   compat_sys_symlinkat
+298  common     readlinkat              sys_readlinkat                  compat_sys_readlinkat
+299  common     fchmodat                sys_fchmodat                    compat_sys_fchmodat
+300  common     faccessat               sys_faccessat                   compat_sys_faccessat
+301  common     pselect6                sys_pselect6                    compat_sys_pselect6
+302  common     ppoll                   sys_ppoll                       compat_sys_ppoll
+303  common     unshare                 sys_unshare                     compat_sys_unshare
+304  common     set_robust_list         sys_set_robust_list             compat_sys_set_robust_list
+305  common     get_robust_list         sys_get_robust_list             compat_sys_get_robust_list
+306  common     splice                  sys_splice                      compat_sys_splice
+307  common     sync_file_range         sys_sync_file_range             compat_sys_s390_sync_file_range
+308  common     tee                     sys_tee                         compat_sys_tee
+309  common     vmsplice                sys_vmsplice                    compat_sys_vmsplice
+310  common     move_pages              sys_move_pages                  compat_sys_move_pages
+311  common     getcpu                  sys_getcpu                      compat_sys_getcpu
+312  common     epoll_pwait             sys_epoll_pwait                 compat_sys_epoll_pwait
+313  common     utimes                  sys_utimes                      compat_sys_utimes
+314  common     fallocate               sys_fallocate                   compat_sys_s390_fallocate
+315  common     utimensat               sys_utimensat                   compat_sys_utimensat
+316  common     signalfd                sys_signalfd                    compat_sys_signalfd
+317  common     timerfd                 -                               -
+318  common     eventfd                 sys_eventfd                     sys_eventfd
+319  common     timerfd_create          sys_timerfd_create              sys_timerfd_create
+320  common     timerfd_settime         sys_timerfd_settime             compat_sys_timerfd_settime
+321  common     timerfd_gettime         sys_timerfd_gettime             compat_sys_timerfd_gettime
+322  common     signalfd4               sys_signalfd4                   compat_sys_signalfd4
+323  common     eventfd2                sys_eventfd2                    sys_eventfd2
+324  common     inotify_init1           sys_inotify_init1               sys_inotify_init1
+325  common     pipe2                   sys_pipe2                       compat_sys_pipe2
+326  common     dup3                    sys_dup3                        sys_dup3
+327  common     epoll_create1           sys_epoll_create1               sys_epoll_create1
+328  common     preadv                  sys_preadv                      compat_sys_preadv
+329  common     pwritev                 sys_pwritev                     compat_sys_pwritev
+330  common     rt_tgsigqueueinfo       sys_rt_tgsigqueueinfo           compat_sys_rt_tgsigqueueinfo
+331  common     perf_event_open         sys_perf_event_open             compat_sys_perf_event_open
+332  common     fanotify_init           sys_fanotify_init               sys_fanotify_init
+333  common     fanotify_mark           sys_fanotify_mark               compat_sys_fanotify_mark
+334  common     prlimit64               sys_prlimit64                   compat_sys_prlimit64
+335  common     name_to_handle_at       sys_name_to_handle_at           compat_sys_name_to_handle_at
+336  common     open_by_handle_at       sys_open_by_handle_at           compat_sys_open_by_handle_at
+337  common     clock_adjtime           sys_clock_adjtime               compat_sys_clock_adjtime
+338  common     syncfs                  sys_syncfs                      sys_syncfs
+339  common     setns                   sys_setns                       sys_setns
+340  common     process_vm_readv        sys_process_vm_readv            compat_sys_process_vm_readv
+341  common     process_vm_writev       sys_process_vm_writev           compat_sys_process_vm_writev
+342  common     s390_runtime_instr      sys_s390_runtime_instr          sys_s390_runtime_instr
+343  common     kcmp                    sys_kcmp                        compat_sys_kcmp
+344  common     finit_module            sys_finit_module                compat_sys_finit_module
+345  common     sched_setattr           sys_sched_setattr               compat_sys_sched_setattr
+346  common     sched_getattr           sys_sched_getattr               compat_sys_sched_getattr
+347  common     renameat2               sys_renameat2                   compat_sys_renameat2
+348  common     seccomp                 sys_seccomp                     compat_sys_seccomp
+349  common     getrandom               sys_getrandom                   compat_sys_getrandom
+350  common     memfd_create            sys_memfd_create                compat_sys_memfd_create
+351  common     bpf                     sys_bpf                         compat_sys_bpf
+352  common     s390_pci_mmio_write     sys_s390_pci_mmio_write         compat_sys_s390_pci_mmio_write
+353  common     s390_pci_mmio_read      sys_s390_pci_mmio_read          compat_sys_s390_pci_mmio_read
+354  common     execveat                sys_execveat                    compat_sys_execveat
+355  common     userfaultfd             sys_userfaultfd                 sys_userfaultfd
+356  common     membarrier              sys_membarrier                  sys_membarrier
+357  common     recvmmsg                sys_recvmmsg                    compat_sys_recvmmsg
+358  common     sendmmsg                sys_sendmmsg                    compat_sys_sendmmsg
+359  common     socket                  sys_socket                      sys_socket
+360  common     socketpair              sys_socketpair                  compat_sys_socketpair
+361  common     bind                    sys_bind                        compat_sys_bind
+362  common     connect                 sys_connect                     compat_sys_connect
+363  common     listen                  sys_listen                      sys_listen
+364  common     accept4                 sys_accept4                     compat_sys_accept4
+365  common     getsockopt              sys_getsockopt                  compat_sys_getsockopt
+366  common     setsockopt              sys_setsockopt                  compat_sys_setsockopt
+367  common     getsockname             sys_getsockname                 compat_sys_getsockname
+368  common     getpeername             sys_getpeername                 compat_sys_getpeername
+369  common     sendto                  sys_sendto                      compat_sys_sendto
+370  common     sendmsg                 sys_sendmsg                     compat_sys_sendmsg
+371  common     recvfrom                sys_recvfrom                    compat_sys_recvfrom
+372  common     recvmsg                 sys_recvmsg                     compat_sys_recvmsg
+373  common     shutdown                sys_shutdown                    sys_shutdown
+374  common     mlock2                  sys_mlock2                      compat_sys_mlock2
+375  common     copy_file_range         sys_copy_file_range             compat_sys_copy_file_range
+376  common     preadv2                 sys_preadv2                     compat_sys_preadv2
+377  common     pwritev2                sys_pwritev2                    compat_sys_pwritev2
+378  common     s390_guarded_storage    sys_s390_guarded_storage        compat_sys_s390_guarded_storage
+379  common     statx                   sys_statx                       compat_sys_statx
+380  common     s390_sthyi              sys_s390_sthyi                  compat_sys_s390_sthyi
diff --git a/tools/perf/builtin-c2c.c b/tools/perf/builtin-c2c.c
index c0815a37fdb5..539c3d460158 100644
--- a/tools/perf/builtin-c2c.c
+++ b/tools/perf/builtin-c2c.c
@@ -2245,7 +2245,7 @@ static int perf_c2c__browse_cacheline(struct hist_entry *he)
         c2c_browser__update_nr_entries(browser);
 
         while (1) {
-                key = hist_browser__run(browser, "? - help");
+                key = hist_browser__run(browser, "? - help", true);
 
                 switch (key) {
                 case 's':
@@ -2314,7 +2314,7 @@ static int perf_c2c__hists_browse(struct hists *hists)
         c2c_browser__update_nr_entries(browser);
 
         while (1) {
-                key = hist_browser__run(browser, "? - help");
+                key = hist_browser__run(browser, "? - help", true);
 
                 switch (key) {
                 case 'q':
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index bf4ca749d1ac..a217623fec2e 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -881,6 +881,15 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
                 }
         }
 
+        /*
+         * If we have just single event and are sending data
+         * through pipe, we need to force the ids allocation,
+         * because we synthesize event name through the pipe
+         * and need the id for that.
+         */
+        if (data->is_pipe && rec->evlist->nr_entries == 1)
+                rec->opts.sample_id = true;
+
         if (record__open(rec) != 0) {
                 err = -1;
                 goto out_child;
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 42a52dcc41cd..4ad5dc649716 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -530,7 +530,8 @@ static int report__browse_hists(struct report *rep)
         case 1:
                 ret = perf_evlist__tui_browse_hists(evlist, help, NULL,
                                                     rep->min_percent,
-                                                    &session->header.env);
+                                                    &session->header.env,
+                                                    true);
                 /*
                  * Usually "ret" is the last pressed key, and we only
                  * care if the key notifies us to switch data file.
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 98bf9d32f222..54a4c152edb3 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -917,7 +917,7 @@ static void print_metric_csv(void *ctx,
         char buf[64], *vals, *ends;
 
         if (unit == NULL || fmt == NULL) {
-                fprintf(out, "%s%s%s%s", csv_sep, csv_sep, csv_sep, csv_sep);
+                fprintf(out, "%s%s", csv_sep, csv_sep);
                 return;
         }
         snprintf(buf, sizeof(buf), fmt, val);
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index c6ccda52117d..35ac016fcb98 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -283,8 +283,9 @@ static void perf_top__print_sym_table(struct perf_top *top)
 
         printf("%-*.*s\n", win_width, win_width, graph_dotted_line);
 
-        if (hists->stats.nr_lost_warned !=
-            hists->stats.nr_events[PERF_RECORD_LOST]) {
+        if (!top->record_opts.overwrite &&
+            (hists->stats.nr_lost_warned !=
+            hists->stats.nr_events[PERF_RECORD_LOST])) {
                 hists->stats.nr_lost_warned =
                               hists->stats.nr_events[PERF_RECORD_LOST];
                 color_fprintf(stdout, PERF_COLOR_RED,
@@ -611,7 +612,8 @@ static void *display_thread_tui(void *arg)
 
         perf_evlist__tui_browse_hists(top->evlist, help, &hbt,
                                       top->min_percent,
-                                      &top->session->header.env);
+                                      &top->session->header.env,
+                                      !top->record_opts.overwrite);
 
         done = 1;
         return NULL;
@@ -807,15 +809,23 @@ static void perf_event__process_sample(struct perf_tool *tool,
 
 static void perf_top__mmap_read_idx(struct perf_top *top, int idx)
 {
+        struct record_opts *opts = &top->record_opts;
+        struct perf_evlist *evlist = top->evlist;
         struct perf_sample sample;
         struct perf_evsel *evsel;
+        struct perf_mmap *md;
         struct perf_session *session = top->session;
         union perf_event *event;
         struct machine *machine;
+        u64 end, start;
         int ret;
 
-        while ((event = perf_evlist__mmap_read(top->evlist, idx)) != NULL) {
-                ret = perf_evlist__parse_sample(top->evlist, event, &sample);
+        md = opts->overwrite ? &evlist->overwrite_mmap[idx] : &evlist->mmap[idx];
+        if (perf_mmap__read_init(md, opts->overwrite, &start, &end) < 0)
+                return;
+
+        while ((event = perf_mmap__read_event(md, opts->overwrite, &start, end)) != NULL) {
+                ret = perf_evlist__parse_sample(evlist, event, &sample);
                 if (ret) {
                         pr_err("Can't parse sample, err = %d\n", ret);
                         goto next_event;
@@ -869,16 +879,120 @@ static void perf_top__mmap_read_idx(struct perf_top *top, int idx)
                 } else
                         ++session->evlist->stats.nr_unknown_events;
 next_event:
-                perf_evlist__mmap_consume(top->evlist, idx);
+                perf_mmap__consume(md, opts->overwrite);
         }
+
+        perf_mmap__read_done(md);
 }
 
 static void perf_top__mmap_read(struct perf_top *top)
 {
+        bool overwrite = top->record_opts.overwrite;
+        struct perf_evlist *evlist = top->evlist;
+        unsigned long long start, end;
         int i;
 
+        start = rdclock();
+        if (overwrite)
+                perf_evlist__toggle_bkw_mmap(evlist, BKW_MMAP_DATA_PENDING);
+
         for (i = 0; i < top->evlist->nr_mmaps; i++)
                 perf_top__mmap_read_idx(top, i);
+
+        if (overwrite) {
+                perf_evlist__toggle_bkw_mmap(evlist, BKW_MMAP_EMPTY);
+                perf_evlist__toggle_bkw_mmap(evlist, BKW_MMAP_RUNNING);
+        }
+        end = rdclock();
+
+        if ((end - start) > (unsigned long long)top->delay_secs * NSEC_PER_SEC)
+                ui__warning("Too slow to read ring buffer.\n"
+                            "Please try increasing the period (-c) or\n"
+                            "decreasing the freq (-F) or\n"
+                            "limiting the number of CPUs (-C)\n");
+}
+
+/*
+ * Check per-event overwrite term.
+ * perf top should support consistent term for all events.
+ * - All events don't have per-event term
+ *   E.g. "cpu/cpu-cycles/,cpu/instructions/"
+ *   Nothing change, return 0.
+ * - All events have same per-event term
+ *   E.g. "cpu/cpu-cycles,no-overwrite/,cpu/instructions,no-overwrite/
+ *   Using the per-event setting to replace the opts->overwrite if
+ *   they are different, then return 0.
+ * - Events have different per-event term
+ *   E.g. "cpu/cpu-cycles,overwrite/,cpu/instructions,no-overwrite/"
+ *   Return -1
+ * - Some of the event set per-event term, but some not.
+ *   E.g. "cpu/cpu-cycles/,cpu/instructions,no-overwrite/"
+ *   Return -1
+ */
+static int perf_top__overwrite_check(struct perf_top *top)
+{
+        struct record_opts *opts = &top->record_opts;
+        struct perf_evlist *evlist = top->evlist;
+        struct perf_evsel_config_term *term;
+        struct list_head *config_terms;
+        struct perf_evsel *evsel;
+        int set, overwrite = -1;
+
+        evlist__for_each_entry(evlist, evsel) {
+                set = -1;
+                config_terms = &evsel->config_terms;
+                list_for_each_entry(term, config_terms, list) {
+                        if (term->type == PERF_EVSEL__CONFIG_TERM_OVERWRITE)
+                                set = term->val.overwrite ? 1 : 0;
+                }
+
+                /* no term for current and previous event (likely) */
+                if ((overwrite < 0) && (set < 0))
+                        continue;
+
+                /* has term for both current and previous event, compare */
+                if ((overwrite >= 0) && (set >= 0) && (overwrite != set))
+                        return -1;
+
+                /* no term for current event but has term for previous one */
+                if ((overwrite >= 0) && (set < 0))
+                        return -1;
+
+                /* has term for current event */
+                if ((overwrite < 0) && (set >= 0)) {
+                        /* if it's first event, set overwrite */
+                        if (evsel == perf_evlist__first(evlist))
+                                overwrite = set;
+                        else
+                                return -1;
+                }
+        }
+
+        if ((overwrite >= 0) && (opts->overwrite != overwrite))
+                opts->overwrite = overwrite;
+
+        return 0;
+}
+
+static int perf_top_overwrite_fallback(struct perf_top *top,
+                                       struct perf_evsel *evsel)
+{
+        struct record_opts *opts = &top->record_opts;
+        struct perf_evlist *evlist = top->evlist;
+        struct perf_evsel *counter;
+
+        if (!opts->overwrite)
+                return 0;
+
+        /* only fall back when first event fails */
+        if (evsel != perf_evlist__first(evlist))
+                return 0;
+
+        evlist__for_each_entry(evlist, counter)
+                counter->attr.write_backward = false;
+        opts->overwrite = false;
+        pr_debug2("fall back to non-overwrite mode\n");
+        return 1;
 }
 
 static int perf_top__start_counters(struct perf_top *top)
@@ -888,12 +1002,33 @@ static int perf_top__start_counters(struct perf_top *top)
         struct perf_evlist *evlist = top->evlist;
         struct record_opts *opts = &top->record_opts;
 
+        if (perf_top__overwrite_check(top)) {
+                ui__error("perf top only support consistent per-event "
+                          "overwrite setting for all events\n");
+                goto out_err;
+        }
+
         perf_evlist__config(evlist, opts, &callchain_param);
 
         evlist__for_each_entry(evlist, counter) {
 try_again:
                 if (perf_evsel__open(counter, top->evlist->cpus,
                                      top->evlist->threads) < 0) {
+
+                        /*
+                         * Specially handle overwrite fall back.
+                         * Because perf top is the only tool which has
+                         * overwrite mode by default, support
+                         * both overwrite and non-overwrite mode, and
+                         * require consistent mode for all events.
+                         *
+                         * May move it to generic code with more tools
+                         * have similar attribute.
+                         */
+                        if (perf_missing_features.write_backward &&
+                            perf_top_overwrite_fallback(top, counter))
+                                goto try_again;
+
                         if (perf_evsel__fallback(counter, errno, msg, sizeof(msg))) {
                                 if (verbose > 0)
                                         ui__warning("%s\n", msg);
@@ -1033,7 +1168,7 @@ static int __cmd_top(struct perf_top *top)
 
                 perf_top__mmap_read(top);
 
-                if (hits == top->samples)
+                if (opts->overwrite || (hits == top->samples))
                         ret = perf_evlist__poll(top->evlist, 100);
 
                 if (resize) {
@@ -1127,6 +1262,7 @@ int cmd_top(int argc, const char **argv)
                                 .uses_mmap   = true,
                         },
                         .proc_map_timeout    = 500,
+                        .overwrite      = 1,
                 },
                 .max_stack           = sysctl_perf_event_max_stack,
                 .sym_pcnt_filter     = 5,
diff --git a/tools/perf/check-headers.sh b/tools/perf/check-headers.sh
index 51abdb0a4047..790ec25919a0 100755
--- a/tools/perf/check-headers.sh
+++ b/tools/perf/check-headers.sh
@@ -33,7 +33,6 @@ arch/s390/include/uapi/asm/kvm.h
 arch/s390/include/uapi/asm/kvm_perf.h
 arch/s390/include/uapi/asm/ptrace.h
 arch/s390/include/uapi/asm/sie.h
-arch/s390/include/uapi/asm/unistd.h
 arch/arm/include/uapi/asm/kvm.h
 arch/arm64/include/uapi/asm/kvm.h
 arch/alpha/include/uapi/asm/errno.h
diff --git a/tools/perf/perf.h b/tools/perf/perf.h
index cfe46236a5e5..57b9b342d533 100644
--- a/tools/perf/perf.h
+++ b/tools/perf/perf.h
@@ -61,6 +61,7 @@ struct record_opts {
         bool         tail_synthesize;
         bool         overwrite;
         bool         ignore_missing_thread;
+        bool         sample_id;
         unsigned int freq;
         unsigned int mmap_pages;
         unsigned int auxtrace_mmap_pages;
diff --git a/tools/perf/pmu-events/arch/arm64/cortex-a53/branch.json b/tools/perf/pmu-events/arch/arm64/cortex-a53/branch.json
new file mode 100644
index 000000000000..3b6208763e50
--- /dev/null
+++ b/tools/perf/pmu-events/arch/arm64/cortex-a53/branch.json
@@ -0,0 +1,27 @@
+[
+  {,
+    "EventCode": "0x7A",
+    "EventName": "BR_INDIRECT_SPEC",
+    "BriefDescription": "Branch speculatively executed - Indirect branch"
+  },
+  {,
+    "EventCode": "0xC9",
+    "EventName": "BR_COND",
+    "BriefDescription": "Conditional branch executed"
+  },
+  {,
+    "EventCode": "0xCA",
+    "EventName": "BR_INDIRECT_MISPRED",
+    "BriefDescription": "Indirect branch mispredicted"
+  },
+  {,
+    "EventCode": "0xCB",
+    "EventName": "BR_INDIRECT_MISPRED_ADDR",
+    "BriefDescription": "Indirect branch mispredicted because of address miscompare"
+  },
+  {,
+    "EventCode": "0xCC",
+    "EventName": "BR_COND_MISPRED",
+    "BriefDescription": "Conditional branch mispredicted"
+  }
+]
diff --git a/tools/perf/pmu-events/arch/arm64/cortex-a53/bus.json b/tools/perf/pmu-events/arch/arm64/cortex-a53/bus.json
new file mode 100644
index 000000000000..480d9f7460ab
--- /dev/null
+++ b/tools/perf/pmu-events/arch/arm64/cortex-a53/bus.json
@@ -0,0 +1,22 @@
+[
+  {,
+    "EventCode": "0x60",
+    "EventName": "BUS_ACCESS_LD",
+    "BriefDescription": "Bus access - Read"
+  },
+  {,
+    "EventCode": "0x61",
+    "EventName": "BUS_ACCESS_ST",
+    "BriefDescription": "Bus access - Write"
+  },
+  {,
+    "EventCode": "0xC0",
+    "EventName": "EXT_MEM_REQ",
+    "BriefDescription": "External memory request"
+  },
+  {,
+    "EventCode": "0xC1",
+    "EventName": "EXT_MEM_REQ_NC",
+    "BriefDescription": "Non-cacheable external memory request"
+  }
+]
diff --git a/tools/perf/pmu-events/arch/arm64/cortex-a53/cache.json b/tools/perf/pmu-events/arch/arm64/cortex-a53/cache.json
new file mode 100644
index 000000000000..11baad6344b9
--- /dev/null
+++ b/tools/perf/pmu-events/arch/arm64/cortex-a53/cache.json
@@ -0,0 +1,27 @@
+[
+  {,
+    "EventCode": "0xC2",
+    "EventName": "PREFETCH_LINEFILL",
+    "BriefDescription": "Linefill because of prefetch"
+  },
+  {,
+    "EventCode": "0xC3",
+    "EventName": "PREFETCH_LINEFILL_DROP",
+    "BriefDescription": "Instruction Cache Throttle occurred"
+  },
+  {,
+    "EventCode": "0xC4",
+    "EventName": "READ_ALLOC_ENTER",
+    "BriefDescription": "Entering read allocate mode"
+  },
+  {,
+    "EventCode": "0xC5",
+    "EventName": "READ_ALLOC",
+    "BriefDescription": "Read allocate mode"
+  },
+  {,
+    "EventCode": "0xC8",
+    "EventName": "EXT_SNOOP",
+    "BriefDescription": "SCU Snooped data from another CPU for this CPU"
+  }
+]
diff --git a/tools/perf/pmu-events/arch/arm64/cortex-a53/memory.json b/tools/perf/pmu-events/arch/arm64/cortex-a53/memory.json
new file mode 100644
index 000000000000..480d9f7460ab
--- /dev/null
+++ b/tools/perf/pmu-events/arch/arm64/cortex-a53/memory.json
@@ -0,0 +1,22 @@
+[
+  {,
+    "EventCode": "0x60",
+    "EventName": "BUS_ACCESS_LD",
+    "BriefDescription": "Bus access - Read"
+  },
+  {,
+    "EventCode": "0x61",
+    "EventName": "BUS_ACCESS_ST",
+    "BriefDescription": "Bus access - Write"
+  },
+  {,
+    "EventCode": "0xC0",
+    "EventName": "EXT_MEM_REQ",
+    "BriefDescription": "External memory request"
+  },
+  {,
+    "EventCode": "0xC1",
+    "EventName": "EXT_MEM_REQ_NC",
+    "BriefDescription": "Non-cacheable external memory request"
+  }
+]
diff --git a/tools/perf/pmu-events/arch/arm64/cortex-a53/other.json b/tools/perf/pmu-events/arch/arm64/cortex-a53/other.json
new file mode 100644
index 000000000000..73a22402d003
--- /dev/null
+++ b/tools/perf/pmu-events/arch/arm64/cortex-a53/other.json
@@ -0,0 +1,32 @@
+[
+  {,
+    "EventCode": "0x86",
+    "EventName": "EXC_IRQ",
+    "BriefDescription": "Exception taken, IRQ"
+  },
+  {,
+    "EventCode": "0x87",
+    "EventName": "EXC_FIQ",
+    "BriefDescription": "Exception taken, FIQ"
+  },
+  {,
+    "EventCode": "0xC6",
+    "EventName": "PRE_DECODE_ERR",
+    "BriefDescription": "Pre-decode error"
+  },
+  {,
+    "EventCode": "0xD0",
+    "EventName": "L1I_CACHE_ERR",
+    "BriefDescription": "L1 Instruction Cache (data or tag) memory error"
+  },
+  {,
+    "EventCode": "0xD1",
+    "EventName": "L1D_CACHE_ERR",
+    "BriefDescription": "L1 Data Cache (data, tag or dirty) memory error, correctable or non-correctable"
+  },
+  {,
+    "EventCode": "0xD2",
+    "EventName": "TLB_ERR",
+    "BriefDescription": "TLB memory error"
+  }
+]
diff --git a/tools/perf/pmu-events/arch/arm64/cortex-a53/pipeline.json b/tools/perf/pmu-events/arch/arm64/cortex-a53/pipeline.json
new file mode 100644
index 000000000000..3149fb90555a
--- /dev/null
+++ b/tools/perf/pmu-events/arch/arm64/cortex-a53/pipeline.json
@@ -0,0 +1,52 @@
+[
+  {,
+    "EventCode": "0xC7",
+    "EventName": "STALL_SB_FULL",
+    "BriefDescription": "Data Write operation that stalls the pipeline because the store buffer is full"
+  },
+  {,
+    "EventCode": "0xE0",
+    "EventName": "OTHER_IQ_DEP_STALL",
+    "BriefDescription": "Cycles that the DPU IQ is empty and that is not because of a recent micro-TLB miss, instruction cache miss or pre-decode error"
+  },
+  {,
+    "EventCode": "0xE1",
+    "EventName": "IC_DEP_STALL",
+    "BriefDescription": "Cycles the DPU IQ is empty and there is an instruction cache miss being processed"
+  },
+  {,
+    "EventCode": "0xE2",
+    "EventName": "IUTLB_DEP_STALL",
+    "BriefDescription": "Cycles the DPU IQ is empty and there is an instruction micro-TLB miss being processed"
+  },
+  {,
+    "EventCode": "0xE3",
+    "EventName": "DECODE_DEP_STALL",
+    "BriefDescription": "Cycles the DPU IQ is empty and there is a pre-decode error being processed"
+  },
+  {,
+    "EventCode": "0xE4",
+    "EventName": "OTHER_INTERLOCK_STALL",
+    "BriefDescription": "Cycles there is an interlock other than  Advanced SIMD/Floating-point instructions or load/store instruction"
+  },
+  {,
+    "EventCode": "0xE5",
+    "EventName": "AGU_DEP_STALL",
+    "BriefDescription": "Cycles there is an interlock for a load/store instruction waiting for data to calculate the address in the AGU"
+  },
+  {,
+    "EventCode": "0xE6",
+    "EventName": "SIMD_DEP_STALL",
+    "BriefDescription": "Cycles there is an interlock for an Advanced SIMD/Floating-point operation."
+  },
+  {,
+    "EventCode": "0xE7",
+    "EventName": "LD_DEP_STALL",
+    "BriefDescription": "Cycles there is a stall in the Wr stage because of a load miss"
+  },
+  {,
+    "EventCode": "0xE8",
+    "EventName": "ST_DEP_STALL",
+    "BriefDescription": "Cycles there is a stall in the Wr stage because of a store"
+  }
+]
diff --git a/tools/perf/pmu-events/arch/arm64/mapfile.csv b/tools/perf/pmu-events/arch/arm64/mapfile.csv
index 219d6756134e..e61c9ca6cf9e 100644
--- a/tools/perf/pmu-events/arch/arm64/mapfile.csv
+++ b/tools/perf/pmu-events/arch/arm64/mapfile.csv
@@ -13,3 +13,4 @@
 #
 #Family-model,Version,Filename,EventType
 0x00000000420f5160,v1,cavium,core
+0x00000000410fd03[[:xdigit:]],v1,cortex-a53,core
diff --git a/tools/perf/tests/backward-ring-buffer.c b/tools/perf/tests/backward-ring-buffer.c
index 4035d43523c3..e0b1b414d466 100644
--- a/tools/perf/tests/backward-ring-buffer.c
+++ b/tools/perf/tests/backward-ring-buffer.c
@@ -31,10 +31,12 @@ static int count_samples(struct perf_evlist *evlist, int *sample_count,
         int i;
 
         for (i = 0; i < evlist->nr_mmaps; i++) {
+                struct perf_mmap *map = &evlist->overwrite_mmap[i];
                 union perf_event *event;
+                u64 start, end;
 
-                perf_mmap__read_catchup(&evlist->overwrite_mmap[i]);
-                while ((event = perf_mmap__read_backward(&evlist->overwrite_mmap[i])) != NULL) {
+                perf_mmap__read_init(map, true, &start, &end);
+                while ((event = perf_mmap__read_event(map, true, &start, end)) != NULL) {
                         const u32 type = event->header.type;
 
                         switch (type) {
@@ -49,6 +51,7 @@ static int count_samples(struct perf_evlist *evlist, int *sample_count,
                                 return TEST_FAIL;
                         }
                 }
+                perf_mmap__read_done(map);
         }
         return TEST_OK;
 }
diff --git a/tools/perf/tests/shell/trace+probe_libc_inet_pton.sh b/tools/perf/tests/shell/trace+probe_libc_inet_pton.sh
index 8b3da21a08f1..c446c894b297 100755
--- a/tools/perf/tests/shell/trace+probe_libc_inet_pton.sh
+++ b/tools/perf/tests/shell/trace+probe_libc_inet_pton.sh
@@ -22,10 +22,23 @@ trace_libc_inet_pton_backtrace() {
         expected[4]="rtt min.*"
         expected[5]="[0-9]+\.[0-9]+[[:space:]]+probe_libc:inet_pton:\([[:xdigit:]]+\)"
         expected[6]=".*inet_pton[[:space:]]\($libc\)$"
-        expected[7]="getaddrinfo[[:space:]]\($libc\)$"
-        expected[8]=".*\(.*/bin/ping.*\)$"
-
-        perf trace --no-syscalls -e probe_libc:inet_pton/max-stack=3/ ping -6 -c 1 ::1 2>&1 | grep -v ^$ | while read line ; do
+        case "$(uname -m)" in
+        s390x)
+                eventattr='call-graph=dwarf'
+                expected[7]="gaih_inet[[:space:]]\(inlined\)$"
+                expected[8]="__GI_getaddrinfo[[:space:]]\(inlined\)$"
+                expected[9]="main[[:space:]]\(.*/bin/ping.*\)$"
+                expected[10]="__libc_start_main[[:space:]]\($libc\)$"
+                expected[11]="_start[[:space:]]\(.*/bin/ping.*\)$"
+                ;;
+        *)
+                eventattr='max-stack=3'
+                expected[7]="getaddrinfo[[:space:]]\($libc\)$"
+                expected[8]=".*\(.*/bin/ping.*\)$"
+                ;;
+        esac
+
+        perf trace --no-syscalls -e probe_libc:inet_pton/$eventattr/ ping -6 -c 1 ::1 2>&1 | grep -v ^$ | while read line ; do
                 echo $line
                 echo "$line" | egrep -q "${expected[$idx]}"
                 if [ $? -ne 0 ] ; then
@@ -33,7 +46,7 @@ trace_libc_inet_pton_backtrace() {
                         exit 1
                 fi
                 let idx+=1
-                [ $idx -eq 9 ] && break
+                [ -z "${expected[$idx]}" ] && break
         done
 }
 
diff --git a/tools/perf/ui/browsers/annotate.c b/tools/perf/ui/browsers/annotate.c
index 286427975112..fbf927cf775d 100644
--- a/tools/perf/ui/browsers/annotate.c
+++ b/tools/perf/ui/browsers/annotate.c
@@ -327,7 +327,32 @@ static void annotate_browser__draw_current_jump(struct ui_browser *browser)
         if (!disasm_line__is_valid_jump(cursor, sym))
                 return;
 
+        /*
+         * This first was seen with a gcc function, _cpp_lex_token, that
+         * has the usual jumps:
+         *
+         *  │1159e6c: ↓ jne    115aa32 <_cpp_lex_token@@Base+0xf92>
+         *
+         * I.e. jumps to a label inside that function (_cpp_lex_token), and
+         * those works, but also this kind:
+         *
+         *  │1159e8b: ↓ jne    c469be <cpp_named_operator2name@@Base+0xa72>
+         *
+         *  I.e. jumps to another function, outside _cpp_lex_token, which
+         *  are not being correctly handled generating as a side effect references
+         *  to ab->offset[] entries that are set to NULL, so to make this code
+         *  more robust, check that here.
+         *
+         *  A proper fix for will be put in place, looking at the function
+         *  name right after the '<' token and probably treating this like a
+         *  'call' instruction.
+         */
         target = ab->offsets[cursor->ops.target.offset];
+        if (target == NULL) {
+                ui_helpline__printf("WARN: jump target inconsistency, press 'o', ab->offsets[%#x] = NULL\n",
+                                    cursor->ops.target.offset);
+                return;
+        }
 
         bcursor = browser_line(&cursor->al);
         btarget = browser_line(target);
diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c
index 68146f4620a5..6495ee55d9c3 100644
--- a/tools/perf/ui/browsers/hists.c
+++ b/tools/perf/ui/browsers/hists.c
@@ -608,7 +608,8 @@ static int hist_browser__title(struct hist_browser *browser, char *bf, size_t si
         return browser->title ? browser->title(browser, bf, size) : 0;
 }
 
-int hist_browser__run(struct hist_browser *browser, const char *help)
+int hist_browser__run(struct hist_browser *browser, const char *help,
+                      bool warn_lost_event)
 {
         int key;
         char title[160];
@@ -638,8 +639,9 @@ int hist_browser__run(struct hist_browser *browser, const char *help)
                         nr_entries = hist_browser__nr_entries(browser);
                         ui_browser__update_nr_entries(&browser->b, nr_entries);
 
-                        if (browser->hists->stats.nr_lost_warned !=
-                            browser->hists->stats.nr_events[PERF_RECORD_LOST]) {
+                        if (warn_lost_event &&
+                            (browser->hists->stats.nr_lost_warned !=
+                            browser->hists->stats.nr_events[PERF_RECORD_LOST])) {
                                 browser->hists->stats.nr_lost_warned =
                                         browser->hists->stats.nr_events[PERF_RECORD_LOST];
                                 ui_browser__warn_lost_events(&browser->b);
@@ -2763,7 +2765,8 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
                                     bool left_exits,
                                     struct hist_browser_timer *hbt,
                                     float min_pcnt,
-                                    struct perf_env *env)
+                                    struct perf_env *env,
+                                    bool warn_lost_event)
 {
         struct hists *hists = evsel__hists(evsel);
         struct hist_browser *browser = perf_evsel_browser__new(evsel, hbt, env);
@@ -2844,7 +2847,8 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
 
                 nr_options = 0;
 
-                key = hist_browser__run(browser, helpline);
+                key = hist_browser__run(browser, helpline,
+                                        warn_lost_event);
 
                 if (browser->he_selection != NULL) {
                         thread = hist_browser__selected_thread(browser);
@@ -3184,7 +3188,8 @@ static void perf_evsel_menu__write(struct ui_browser *browser,
 
 static int perf_evsel_menu__run(struct perf_evsel_menu *menu,
                                 int nr_events, const char *help,
-                                struct hist_browser_timer *hbt)
+                                struct hist_browser_timer *hbt,
+                                bool warn_lost_event)
 {
         struct perf_evlist *evlist = menu->b.priv;
         struct perf_evsel *pos;
@@ -3203,7 +3208,9 @@ static int perf_evsel_menu__run(struct perf_evsel_menu *menu,
                 case K_TIMER:
                         hbt->timer(hbt->arg);
 
-                        if (!menu->lost_events_warned && menu->lost_events) {
+                        if (!menu->lost_events_warned &&
+                            menu->lost_events &&
+                            warn_lost_event) {
                                 ui_browser__warn_lost_events(&menu->b);
                                 menu->lost_events_warned = true;
                         }
@@ -3224,7 +3231,8 @@ browse_hists:
                         key = perf_evsel__hists_browse(pos, nr_events, help,
                                                        true, hbt,
                                                        menu->min_pcnt,
-                                                       menu->env);
+                                                       menu->env,
+                                                       warn_lost_event);
                         ui_browser__show_title(&menu->b, title);
                         switch (key) {
                         case K_TAB:
@@ -3282,7 +3290,8 @@ static int __perf_evlist__tui_browse_hists(struct perf_evlist *evlist,
                                            int nr_entries, const char *help,
                                            struct hist_browser_timer *hbt,
                                            float min_pcnt,
-                                           struct perf_env *env)
+                                           struct perf_env *env,
+                                           bool warn_lost_event)
 {
         struct perf_evsel *pos;
         struct perf_evsel_menu menu = {
@@ -3309,13 +3318,15 @@ static int __perf_evlist__tui_browse_hists(struct perf_evlist *evlist,
                         menu.b.width = line_len;
         }
 
-        return perf_evsel_menu__run(&menu, nr_entries, help, hbt);
+        return perf_evsel_menu__run(&menu, nr_entries, help,
+                                    hbt, warn_lost_event);
 }
 
 int perf_evlist__tui_browse_hists(struct perf_evlist *evlist, const char *help,
                                   struct hist_browser_timer *hbt,
                                   float min_pcnt,
-                                  struct perf_env *env)
+                                  struct perf_env *env,
+                                  bool warn_lost_event)
 {
         int nr_entries = evlist->nr_entries;
 
@@ -3325,7 +3336,7 @@ single_entry:
 
                 return perf_evsel__hists_browse(first, nr_entries, help,
                                                 false, hbt, min_pcnt,
-                                                env);
+                                                env, warn_lost_event);
         }
 
         if (symbol_conf.event_group) {
@@ -3342,5 +3353,6 @@ single_entry:
         }
 
         return __perf_evlist__tui_browse_hists(evlist, nr_entries, help,
-                                               hbt, min_pcnt, env);
+                                               hbt, min_pcnt, env,
+                                               warn_lost_event);
 }
diff --git a/tools/perf/ui/browsers/hists.h b/tools/perf/ui/browsers/hists.h
index ba431777f559..9428bee076f2 100644
--- a/tools/perf/ui/browsers/hists.h
+++ b/tools/perf/ui/browsers/hists.h
@@ -28,7 +28,8 @@ struct hist_browser {
 
 struct hist_browser *hist_browser__new(struct hists *hists);
 void hist_browser__delete(struct hist_browser *browser);
-int hist_browser__run(struct hist_browser *browser, const char *help);
+int hist_browser__run(struct hist_browser *browser, const char *help,
+                      bool warn_lost_event);
 void hist_browser__init(struct hist_browser *browser,
                         struct hists *hists);
 #endif /* _PERF_UI_BROWSER_HISTS_H_ */
diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c
index 9faf3b5367db..6470ea2aa25e 100644
--- a/tools/perf/util/auxtrace.c
+++ b/tools/perf/util/auxtrace.c
@@ -60,6 +60,12 @@
 #include "sane_ctype.h"
 #include "symbol/kallsyms.h"
 
+static bool auxtrace__dont_decode(struct perf_session *session)
+{
+        return !session->itrace_synth_opts ||
+               session->itrace_synth_opts->dont_decode;
+}
+
 int auxtrace_mmap__mmap(struct auxtrace_mmap *mm,
                         struct auxtrace_mmap_params *mp,
                         void *userpg, int fd)
@@ -762,6 +768,9 @@ int auxtrace_queues__process_index(struct auxtrace_queues *queues,
         size_t i;
         int err;
 
+        if (auxtrace__dont_decode(session))
+                return 0;
+
         list_for_each_entry(auxtrace_index, &session->auxtrace_index, list) {
                 for (i = 0; i < auxtrace_index->nr; i++) {
                         ent = &auxtrace_index->entries[i];
@@ -892,12 +901,6 @@ out_free:
         return err;
 }
 
-static bool auxtrace__dont_decode(struct perf_session *session)
-{
-        return !session->itrace_synth_opts ||
-               session->itrace_synth_opts->dont_decode;
-}
-
 int perf_event__process_auxtrace_info(struct perf_tool *tool __maybe_unused,
                                       union perf_event *event,
                                       struct perf_session *session)
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index ac35cd214feb..e5fc14e53c05 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -715,28 +715,11 @@ union perf_event *perf_evlist__mmap_read_forward(struct perf_evlist *evlist, int
         return perf_mmap__read_forward(md);
 }
 
-union perf_event *perf_evlist__mmap_read_backward(struct perf_evlist *evlist, int idx)
-{
-        struct perf_mmap *md = &evlist->mmap[idx];
-
-        /*
-         * No need to check messup for backward ring buffer:
-         * We can always read arbitrary long data from a backward
-         * ring buffer unless we forget to pause it before reading.
-         */
-        return perf_mmap__read_backward(md);
-}
-
 union perf_event *perf_evlist__mmap_read(struct perf_evlist *evlist, int idx)
 {
         return perf_evlist__mmap_read_forward(evlist, idx);
 }
 
-void perf_evlist__mmap_read_catchup(struct perf_evlist *evlist, int idx)
-{
-        perf_mmap__read_catchup(&evlist->mmap[idx]);
-}
-
 void perf_evlist__mmap_consume(struct perf_evlist *evlist, int idx)
 {
         perf_mmap__consume(&evlist->mmap[idx], false);
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index 75f8e0ad5d76..336b838e6957 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -133,10 +133,6 @@ union perf_event *perf_evlist__mmap_read(struct perf_evlist *evlist, int idx);
 
 union perf_event *perf_evlist__mmap_read_forward(struct perf_evlist *evlist,
                                                  int idx);
-union perf_event *perf_evlist__mmap_read_backward(struct perf_evlist *evlist,
-                                                  int idx);
-void perf_evlist__mmap_read_catchup(struct perf_evlist *evlist, int idx);
-
 void perf_evlist__mmap_consume(struct perf_evlist *evlist, int idx);
 
 int perf_evlist__open(struct perf_evlist *evlist);
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index ff359c9ece2e..ef351688b797 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -41,17 +41,7 @@
 
 #include "sane_ctype.h"
 
-static struct {
-        bool sample_id_all;
-        bool exclude_guest;
-        bool mmap2;
-        bool cloexec;
-        bool clockid;
-        bool clockid_wrong;
-        bool lbr_flags;
-        bool write_backward;
-        bool group_read;
-} perf_missing_features;
+struct perf_missing_features perf_missing_features;
 
 static clockid_t clockid;
 
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index 846e41644525..a7487c6d1866 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -149,6 +149,20 @@ union u64_swap {
         u32 val32[2];
 };
 
+struct perf_missing_features {
+        bool sample_id_all;
+        bool exclude_guest;
+        bool mmap2;
+        bool cloexec;
+        bool clockid;
+        bool clockid_wrong;
+        bool lbr_flags;
+        bool write_backward;
+        bool group_read;
+};
+
+extern struct perf_missing_features perf_missing_features;
+
 struct cpu_map;
 struct target;
 struct thread_map;
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index f6630cb95eff..02721b579746 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -430,7 +430,8 @@ int hist_entry__tui_annotate(struct hist_entry *he, struct perf_evsel *evsel,
 int perf_evlist__tui_browse_hists(struct perf_evlist *evlist, const char *help,
                                   struct hist_browser_timer *hbt,
                                   float min_pcnt,
-                                  struct perf_env *env);
+                                  struct perf_env *env,
+                                  bool warn_lost_event);
 int script_browse(const char *script_opt);
 #else
 static inline
@@ -438,7 +439,8 @@ int perf_evlist__tui_browse_hists(struct perf_evlist *evlist __maybe_unused,
                                   const char *help __maybe_unused,
                                   struct hist_browser_timer *hbt __maybe_unused,
                                   float min_pcnt __maybe_unused,
-                                  struct perf_env *env __maybe_unused)
+                                  struct perf_env *env __maybe_unused,
+                                  bool warn_lost_event __maybe_unused)
 {
         return 0;
 }
diff --git a/tools/perf/util/mmap.c b/tools/perf/util/mmap.c
index 05076e683938..91531a7c8fbf 100644
--- a/tools/perf/util/mmap.c
+++ b/tools/perf/util/mmap.c
@@ -22,29 +22,27 @@ size_t perf_mmap__mmap_len(struct perf_mmap *map)
 
 /* When check_messup is true, 'end' must points to a good entry */
 static union perf_event *perf_mmap__read(struct perf_mmap *map,
-                                         u64 start, u64 end, u64 *prev)
+                                         u64 *startp, u64 end)
 {
         unsigned char *data = map->base + page_size;
         union perf_event *event = NULL;
-        int diff = end - start;
+        int diff = end - *startp;
 
         if (diff >= (int)sizeof(event->header)) {
                 size_t size;
 
-                event = (union perf_event *)&data[start & map->mask];
+                event = (union perf_event *)&data[*startp & map->mask];
                 size = event->header.size;
 
-                if (size < sizeof(event->header) || diff < (int)size) {
-                        event = NULL;
-                        goto broken_event;
-                }
+                if (size < sizeof(event->header) || diff < (int)size)
+                        return NULL;
 
                 /*
                  * Event straddles the mmap boundary -- header should always
                  * be inside due to u64 alignment of output.
                  */
-                if ((start & map->mask) + size != ((start + size) & map->mask)) {
-                        unsigned int offset = start;
+                if ((*startp & map->mask) + size != ((*startp + size) & map->mask)) {
+                        unsigned int offset = *startp;
                         unsigned int len = min(sizeof(*event), size), cpy;
                         void *dst = map->event_copy;
 
@@ -59,20 +57,19 @@ static union perf_event *perf_mmap__read(struct perf_mmap *map,
                         event = (union perf_event *)map->event_copy;
                 }
 
-                start += size;
+                *startp += size;
         }
 
-broken_event:
-        if (prev)
-                *prev = start;
-
         return event;
 }
 
+/*
+ * legacy interface for mmap read.
+ * Don't use it. Use perf_mmap__read_event().
+ */
 union perf_event *perf_mmap__read_forward(struct perf_mmap *map)
 {
         u64 head;
-        u64 old = map->prev;
 
         /*
          * Check if event was unmapped due to a POLLHUP/POLLERR.
@@ -82,13 +79,26 @@ union perf_event *perf_mmap__read_forward(struct perf_mmap *map)
 
         head = perf_mmap__read_head(map);
 
-        return perf_mmap__read(map, old, head, &map->prev);
+        return perf_mmap__read(map, &map->prev, head);
 }
 
-union perf_event *perf_mmap__read_backward(struct perf_mmap *map)
+/*
+ * Read event from ring buffer one by one.
+ * Return one event for each call.
+ *
+ * Usage:
+ * perf_mmap__read_init()
+ * while(event = perf_mmap__read_event()) {
+ *      //process the event
+ *      perf_mmap__consume()
+ * }
+ * perf_mmap__read_done()
+ */
+union perf_event *perf_mmap__read_event(struct perf_mmap *map,
+                                        bool overwrite,
+                                        u64 *startp, u64 end)
 {
-        u64 head, end;
-        u64 start = map->prev;
+        union perf_event *event;
 
         /*
          * Check if event was unmapped due to a POLLHUP/POLLERR.
@@ -96,40 +106,19 @@ union perf_event *perf_mmap__read_backward(struct perf_mmap *map)
         if (!refcount_read(&map->refcnt))
                 return NULL;
 
-        head = perf_mmap__read_head(map);
-        if (!head)
+        if (startp == NULL)
                 return NULL;
 
-        /*
-         * 'head' pointer starts from 0. Kernel minus sizeof(record) form
-         * it each time when kernel writes to it, so in fact 'head' is
-         * negative. 'end' pointer is made manually by adding the size of
-         * the ring buffer to 'head' pointer, means the validate data can
-         * read is the whole ring buffer. If 'end' is positive, the ring
-         * buffer has not fully filled, so we must adjust 'end' to 0.
-         *
-         * However, since both 'head' and 'end' is unsigned, we can't
-         * simply compare 'end' against 0. Here we compare '-head' and
-         * the size of the ring buffer, where -head is the number of bytes
-         * kernel write to the ring buffer.
-         */
-        if (-head < (u64)(map->mask + 1))
-                end = 0;
-        else
-                end = head + map->mask + 1;
-
-        return perf_mmap__read(map, start, end, &map->prev);
-}
+        /* non-overwirte doesn't pause the ringbuffer */
+        if (!overwrite)
+                end = perf_mmap__read_head(map);
 
-void perf_mmap__read_catchup(struct perf_mmap *map)
-{
-        u64 head;
+        event = perf_mmap__read(map, startp, end);
 
-        if (!refcount_read(&map->refcnt))
-                return;
+        if (!overwrite)
+                map->prev = *startp;
 
-        head = perf_mmap__read_head(map);
-        map->prev = head;
+        return event;
 }
 
 static bool perf_mmap__empty(struct perf_mmap *map)
@@ -267,41 +256,60 @@ static int overwrite_rb_find_range(void *buf, int mask, u64 head, u64 *start, u6
         return -1;
 }
 
-int perf_mmap__push(struct perf_mmap *md, bool overwrite,
-                    void *to, int push(void *to, void *buf, size_t size))
+/*
+ * Report the start and end of the available data in ringbuffer
+ */
+int perf_mmap__read_init(struct perf_mmap *md, bool overwrite,
+                         u64 *startp, u64 *endp)
 {
         u64 head = perf_mmap__read_head(md);
         u64 old = md->prev;
-        u64 end = head, start = old;
         unsigned char *data = md->base + page_size;
         unsigned long size;
-        void *buf;
-        int rc = 0;
 
-        start = overwrite ? head : old;
-        end = overwrite ? old : head;
+        *startp = overwrite ? head : old;
+        *endp = overwrite ? old : head;
 
-        if (start == end)
-                return 0;
+        if (*startp == *endp)
+                return -EAGAIN;
 
-        size = end - start;
+        size = *endp - *startp;
         if (size > (unsigned long)(md->mask) + 1) {
                 if (!overwrite) {
                         WARN_ONCE(1, "failed to keep up with mmap data. (warn only once)\n");
 
                         md->prev = head;
                         perf_mmap__consume(md, overwrite);
-                        return 0;
+                        return -EAGAIN;
                 }
 
                 /*
                  * Backward ring buffer is full. We still have a chance to read
                  * most of data from it.
                  */
-                if (overwrite_rb_find_range(data, md->mask, head, &start, &end))
-                        return -1;
+                if (overwrite_rb_find_range(data, md->mask, head, startp, endp))
+                        return -EINVAL;
         }
 
+        return 0;
+}
+
+int perf_mmap__push(struct perf_mmap *md, bool overwrite,
+                    void *to, int push(void *to, void *buf, size_t size))
+{
+        u64 head = perf_mmap__read_head(md);
+        u64 end, start;
+        unsigned char *data = md->base + page_size;
+        unsigned long size;
+        void *buf;
+        int rc = 0;
+
+        rc = perf_mmap__read_init(md, overwrite, &start, &end);
+        if (rc < 0)
+                return (rc == -EAGAIN) ? 0 : -1;
+
+        size = end - start;
+
         if ((start & md->mask) + size != (end & md->mask)) {
                 buf = &data[start & md->mask];
                 size = md->mask + 1 - (start & md->mask);
@@ -327,3 +335,14 @@ int perf_mmap__push(struct perf_mmap *md, bool overwrite,
 out:
         return rc;
 }
+
+/*
+ * Mandatory for overwrite mode
+ * The direction of overwrite mode is backward.
+ * The last perf_mmap__read() will set tail to map->prev.
+ * Need to correct the map->prev to head which is the end of next read.
+ */
+void perf_mmap__read_done(struct perf_mmap *map)
+{
+        map->prev = perf_mmap__read_head(map);
+}
diff --git a/tools/perf/util/mmap.h b/tools/perf/util/mmap.h
index e43d7b55a55f..ec7d3a24e276 100644
--- a/tools/perf/util/mmap.h
+++ b/tools/perf/util/mmap.h
@@ -65,8 +65,6 @@ void perf_mmap__put(struct perf_mmap *map);
 
 void perf_mmap__consume(struct perf_mmap *map, bool overwrite);
 
-void perf_mmap__read_catchup(struct perf_mmap *md);
-
 static inline u64 perf_mmap__read_head(struct perf_mmap *mm)
 {
         struct perf_event_mmap_page *pc = mm->base;
@@ -87,11 +85,17 @@ static inline void perf_mmap__write_tail(struct perf_mmap *md, u64 tail)
 }
 
 union perf_event *perf_mmap__read_forward(struct perf_mmap *map);
-union perf_event *perf_mmap__read_backward(struct perf_mmap *map);
+
+union perf_event *perf_mmap__read_event(struct perf_mmap *map,
+                                        bool overwrite,
+                                        u64 *startp, u64 end);
 
 int perf_mmap__push(struct perf_mmap *md, bool backward,
                     void *to, int push(void *to, void *buf, size_t size));
 
 size_t perf_mmap__mmap_len(struct perf_mmap *map);
 
+int perf_mmap__read_init(struct perf_mmap *md, bool overwrite,
+                         u64 *startp, u64 *endp);
+void perf_mmap__read_done(struct perf_mmap *map);
 #endif /*__PERF_MMAP_H */
diff --git a/tools/perf/util/record.c b/tools/perf/util/record.c
index 1e97937b03a9..6f09e4962dad 100644
--- a/tools/perf/util/record.c
+++ b/tools/perf/util/record.c
@@ -137,6 +137,7 @@ void perf_evlist__config(struct perf_evlist *evlist, struct record_opts *opts,
         struct perf_evsel *evsel;
         bool use_sample_identifier = false;
         bool use_comm_exec;
+        bool sample_id = opts->sample_id;
 
         /*
          * Set the evsel leader links before we configure attributes,
@@ -163,8 +164,7 @@ void perf_evlist__config(struct perf_evlist *evlist, struct record_opts *opts,
                  * match the id.
                  */
                 use_sample_identifier = perf_can_sample_identifier();
-                evlist__for_each_entry(evlist, evsel)
-                        perf_evsel__set_sample_id(evsel, use_sample_identifier);
+                sample_id = true;
         } else if (evlist->nr_entries > 1) {
                 struct perf_evsel *first = perf_evlist__first(evlist);
 
@@ -174,6 +174,10 @@ void perf_evlist__config(struct perf_evlist *evlist, struct record_opts *opts,
                         use_sample_identifier = perf_can_sample_identifier();
                         break;
                 }
+                sample_id = true;
+        }
+
+        if (sample_id) {
                 evlist__for_each_entry(evlist, evsel)
                         perf_evsel__set_sample_id(evsel, use_sample_identifier);
         }
diff --git a/tools/perf/util/trigger.h b/tools/perf/util/trigger.h
index 370138e7e35c..88223bc7c82b 100644
--- a/tools/perf/util/trigger.h
+++ b/tools/perf/util/trigger.h
@@ -12,7 +12,7 @@
  * States and transits:
  *
  *
- *  OFF--(on)--> READY --(hit)--> HIT
+ *  OFF--> ON --> READY --(hit)--> HIT
  *                 ^               |
  *                 |            (ready)
  *                 |               |
@@ -27,8 +27,9 @@ struct trigger {
         volatile enum {
                 TRIGGER_ERROR           = -2,
                 TRIGGER_OFF             = -1,
-                TRIGGER_READY           = 0,
-                TRIGGER_HIT             = 1,
+                TRIGGER_ON              = 0,
+                TRIGGER_READY           = 1,
+                TRIGGER_HIT             = 2,
         } state;
         const char *name;
 };
@@ -50,7 +51,7 @@ static inline bool trigger_is_error(struct trigger *t)
 static inline void trigger_on(struct trigger *t)
 {
         TRIGGER_WARN_ONCE(t, TRIGGER_OFF);
-        t->state = TRIGGER_READY;
+        t->state = TRIGGER_ON;
 }
 
 static inline void trigger_ready(struct trigger *t)
diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c
index 443892dabedb..1019bbc5dbd8 100644
--- a/tools/perf/util/util.c
+++ b/tools/perf/util/util.c
@@ -340,35 +340,15 @@ size_t hex_width(u64 v)
         return n;
 }
 
-static int hex(char ch)
-{
-        if ((ch >= '0') && (ch <= '9'))
-                return ch - '0';
-        if ((ch >= 'a') && (ch <= 'f'))
-                return ch - 'a' + 10;
-        if ((ch >= 'A') && (ch <= 'F'))
-                return ch - 'A' + 10;
-        return -1;
-}
-
 /*
  * While we find nice hex chars, build a long_val.
  * Return number of chars processed.
  */
 int hex2u64(const char *ptr, u64 *long_val)
 {
-        const char *p = ptr;
-        *long_val = 0;
-
-        while (*p) {
-                const int hex_val = hex(*p);
+        char *p;
 
-                if (hex_val < 0)
-                        break;
-
-                *long_val = (*long_val << 4) | hex_val;
-                p++;
-        }
+        *long_val = strtoull(ptr, &p, 16);
 
         return p - ptr;
 }
diff --git a/tools/power/acpi/Makefile.config b/tools/power/acpi/Makefile.config
index a1883bbb0144..2cccbba64418 100644
--- a/tools/power/acpi/Makefile.config
+++ b/tools/power/acpi/Makefile.config
@@ -56,9 +56,6 @@ INSTALL_SCRIPT = ${INSTALL_PROGRAM}
 # to compile vs uClibc, that can be done here as well.
 CROSS = #/usr/i386-linux-uclibc/usr/bin/i386-uclibc-
 CROSS_COMPILE ?= $(CROSS)
-CC = $(CROSS_COMPILE)gcc
-LD = $(CROSS_COMPILE)gcc
-STRIP = $(CROSS_COMPILE)strip
 HOSTCC = gcc
 
 # check if compiler option is supported
diff --git a/tools/scripts/Makefile.include b/tools/scripts/Makefile.include
index fcb3ed0be5f8..dd614463d4d6 100644
--- a/tools/scripts/Makefile.include
+++ b/tools/scripts/Makefile.include
@@ -42,6 +42,24 @@ EXTRA_WARNINGS += -Wformat
 
 CC_NO_CLANG := $(shell $(CC) -dM -E -x c /dev/null | grep -Fq "__clang__"; echo $$?)
 
+# Makefiles suck: This macro sets a default value of $(2) for the
+# variable named by $(1), unless the variable has been set by
+# environment or command line. This is necessary for CC and AR
+# because make sets default values, so the simpler ?= approach
+# won't work as expected.
+define allow-override
+  $(if $(or $(findstring environment,$(origin $(1))),\
+            $(findstring command line,$(origin $(1)))),,\
+    $(eval $(1) = $(2)))
+endef
+
+# Allow setting various cross-compile vars or setting CROSS_COMPILE as a prefix.
+$(call allow-override,CC,$(CROSS_COMPILE)gcc)
+$(call allow-override,AR,$(CROSS_COMPILE)ar)
+$(call allow-override,LD,$(CROSS_COMPILE)ld)
+$(call allow-override,CXX,$(CROSS_COMPILE)g++)
+$(call allow-override,STRIP,$(CROSS_COMPILE)strip)
+
 ifeq ($(CC_NO_CLANG), 1)
 EXTRA_WARNINGS += -Wstrict-aliasing=3
 endif
diff --git a/tools/spi/Makefile b/tools/spi/Makefile
index 90615e10c79a..815d15589177 100644
--- a/tools/spi/Makefile
+++ b/tools/spi/Makefile
@@ -11,8 +11,6 @@ endif
 # (this improves performance and avoids hard-to-debug behaviour);
 MAKEFLAGS += -r
 
-CC = $(CROSS_COMPILE)gcc
-LD = $(CROSS_COMPILE)ld
 CFLAGS += -O2 -Wall -g -D_GNU_SOURCE -I$(OUTPUT)include
 
 ALL_TARGETS := spidev_test spidev_fdx
diff --git a/tools/testing/radix-tree/idr-test.c b/tools/testing/radix-tree/idr-test.c
index 44ef9eba5a7a..6c645eb77d42 100644
--- a/tools/testing/radix-tree/idr-test.c
+++ b/tools/testing/radix-tree/idr-test.c
@@ -178,6 +178,55 @@ void idr_get_next_test(int base)
         idr_destroy(&idr);
 }
 
+int idr_u32_cb(int id, void *ptr, void *data)
+{
+        BUG_ON(id < 0);
+        BUG_ON(ptr != DUMMY_PTR);
+        return 0;
+}
+
+void idr_u32_test1(struct idr *idr, u32 handle)
+{
+        static bool warned = false;
+        u32 id = handle;
+        int sid = 0;
+        void *ptr;
+
+        BUG_ON(idr_alloc_u32(idr, DUMMY_PTR, &id, id, GFP_KERNEL));
+        BUG_ON(id != handle);
+        BUG_ON(idr_alloc_u32(idr, DUMMY_PTR, &id, id, GFP_KERNEL) != -ENOSPC);
+        BUG_ON(id != handle);
+        if (!warned && id > INT_MAX)
+                printk("vvv Ignore these warnings\n");
+        ptr = idr_get_next(idr, &sid);
+        if (id > INT_MAX) {
+                BUG_ON(ptr != NULL);
+                BUG_ON(sid != 0);
+        } else {
+                BUG_ON(ptr != DUMMY_PTR);
+                BUG_ON(sid != id);
+        }
+        idr_for_each(idr, idr_u32_cb, NULL);
+        if (!warned && id > INT_MAX) {
+                printk("^^^ Warnings over\n");
+                warned = true;
+        }
+        BUG_ON(idr_remove(idr, id) != DUMMY_PTR);
+        BUG_ON(!idr_is_empty(idr));
+}
+
+void idr_u32_test(int base)
+{
+        DEFINE_IDR(idr);
+        idr_init_base(&idr, base);
+        idr_u32_test1(&idr, 10);
+        idr_u32_test1(&idr, 0x7fffffff);
+        idr_u32_test1(&idr, 0x80000000);
+        idr_u32_test1(&idr, 0x80000001);
+        idr_u32_test1(&idr, 0xffe00000);
+        idr_u32_test1(&idr, 0xffffffff);
+}
+
 void idr_checks(void)
 {
         unsigned long i;
@@ -248,6 +297,9 @@ void idr_checks(void)
         idr_get_next_test(0);
         idr_get_next_test(1);
         idr_get_next_test(4);
+        idr_u32_test(4);
+        idr_u32_test(1);
+        idr_u32_test(0);
 }
 
 /*
diff --git a/tools/testing/radix-tree/linux.c b/tools/testing/radix-tree/linux.c
index 6903ccf35595..44a0d1ad4408 100644
--- a/tools/testing/radix-tree/linux.c
+++ b/tools/testing/radix-tree/linux.c
@@ -29,7 +29,7 @@ void *kmem_cache_alloc(struct kmem_cache *cachep, int flags)
 {
         struct radix_tree_node *node;
 
-        if (flags & __GFP_NOWARN)
+        if (!(flags & __GFP_DIRECT_RECLAIM))
                 return NULL;
 
         pthread_mutex_lock(&cachep->lock);
@@ -73,10 +73,17 @@ void kmem_cache_free(struct kmem_cache *cachep, void *objp)
 
 void *kmalloc(size_t size, gfp_t gfp)
 {
-        void *ret = malloc(size);
+        void *ret;
+
+        if (!(gfp & __GFP_DIRECT_RECLAIM))
+                return NULL;
+
+        ret = malloc(size);
         uatomic_inc(&nr_allocated);
         if (kmalloc_verbose)
                 printf("Allocating %p from malloc\n", ret);
+        if (gfp & __GFP_ZERO)
+                memset(ret, 0, size);
         return ret;
 }
 
diff --git a/tools/testing/radix-tree/linux/compiler_types.h b/tools/testing/radix-tree/linux/compiler_types.h
new file mode 100644
index 000000000000..e69de29bb2d1
--- /dev/null
+++ b/tools/testing/radix-tree/linux/compiler_types.h
diff --git a/tools/testing/radix-tree/linux/gfp.h b/tools/testing/radix-tree/linux/gfp.h
index e9fff59dfd8a..e3201ccf54c3 100644
--- a/tools/testing/radix-tree/linux/gfp.h
+++ b/tools/testing/radix-tree/linux/gfp.h
@@ -11,6 +11,7 @@
 #define __GFP_IO                0x40u
 #define __GFP_FS                0x80u
 #define __GFP_NOWARN            0x200u
+#define __GFP_ZERO              0x8000u
 #define __GFP_ATOMIC            0x80000u
 #define __GFP_ACCOUNT           0x100000u
 #define __GFP_DIRECT_RECLAIM    0x400000u
diff --git a/tools/testing/radix-tree/linux/slab.h b/tools/testing/radix-tree/linux/slab.h
index 979baeec7e70..a037def0dec6 100644
--- a/tools/testing/radix-tree/linux/slab.h
+++ b/tools/testing/radix-tree/linux/slab.h
@@ -3,6 +3,7 @@
 #define SLAB_H
 
 #include <linux/types.h>
+#include <linux/gfp.h>
 
 #define SLAB_HWCACHE_ALIGN 1
 #define SLAB_PANIC 2
@@ -11,6 +12,11 @@
 void *kmalloc(size_t size, gfp_t);
 void kfree(void *);
 
+static inline void *kzalloc(size_t size, gfp_t gfp)
+{
+        return kmalloc(size, gfp | __GFP_ZERO);
+}
+
 void *kmem_cache_alloc(struct kmem_cache *cachep, int flags);
 void kmem_cache_free(struct kmem_cache *cachep, void *objp);
 
diff --git a/tools/testing/selftests/android/Makefile b/tools/testing/selftests/android/Makefile
index 1a7492268993..f6304d2be90c 100644
--- a/tools/testing/selftests/android/Makefile
+++ b/tools/testing/selftests/android/Makefile
@@ -11,11 +11,11 @@ all:
                 BUILD_TARGET=$(OUTPUT)/$$DIR;   \
                 mkdir $$BUILD_TARGET  -p;       \
                 make OUTPUT=$$BUILD_TARGET -C $$DIR $@;\
-                #SUBDIR test prog name should be in the form: SUBDIR_test.sh
+                #SUBDIR test prog name should be in the form: SUBDIR_test.sh \
                 TEST=$$DIR"_test.sh"; \
-                if [ -e $$DIR/$$TEST ]; then
-                        rsync -a $$DIR/$$TEST $$BUILD_TARGET/;
-                fi
+                if [ -e $$DIR/$$TEST ]; then \
+                        rsync -a $$DIR/$$TEST $$BUILD_TARGET/; \
+                fi \
         done
 
 override define RUN_TESTS
diff --git a/tools/testing/selftests/bpf/.gitignore b/tools/testing/selftests/bpf/.gitignore
index cc15af2e54fe..9cf83f895d98 100644
--- a/tools/testing/selftests/bpf/.gitignore
+++ b/tools/testing/selftests/bpf/.gitignore
@@ -11,3 +11,4 @@ test_progs
 test_tcpbpf_user
 test_verifier_log
 feature
+test_libbpf_open
diff --git a/tools/testing/selftests/bpf/test_maps.c b/tools/testing/selftests/bpf/test_maps.c
index 436c4c72414f..9e03a4c356a4 100644
--- a/tools/testing/selftests/bpf/test_maps.c
+++ b/tools/testing/selftests/bpf/test_maps.c
@@ -126,6 +126,8 @@ static void test_hashmap_sizes(int task, void *data)
                         fd = bpf_create_map(BPF_MAP_TYPE_HASH, i, j,
                                             2, map_flags);
                         if (fd < 0) {
+                                if (errno == ENOMEM)
+                                        return;
                                 printf("Failed to create hashmap key=%d value=%d '%s'\n",
                                        i, j, strerror(errno));
                                 exit(1);
diff --git a/tools/testing/selftests/bpf/test_tcpbpf_kern.c b/tools/testing/selftests/bpf/test_tcpbpf_kern.c
index 57119ad57a3f..3e645ee41ed5 100644
--- a/tools/testing/selftests/bpf/test_tcpbpf_kern.c
+++ b/tools/testing/selftests/bpf/test_tcpbpf_kern.c
@@ -5,7 +5,6 @@
 #include <linux/if_ether.h>
 #include <linux/if_packet.h>
 #include <linux/ip.h>
-#include <linux/in6.h>
 #include <linux/types.h>
 #include <linux/socket.h>
 #include <linux/tcp.h>
diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c
index c0f16e93f9bd..437c0b1c9d21 100644
--- a/tools/testing/selftests/bpf/test_verifier.c
+++ b/tools/testing/selftests/bpf/test_verifier.c
@@ -2587,6 +2587,32 @@ static struct bpf_test tests[] = {
                 .result = ACCEPT,
         },
         {
+                "runtime/jit: pass negative index to tail_call",
+                .insns = {
+                        BPF_MOV64_IMM(BPF_REG_3, -1),
+                        BPF_LD_MAP_FD(BPF_REG_2, 0),
+                        BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+                                     BPF_FUNC_tail_call),
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        BPF_EXIT_INSN(),
+                },
+                .fixup_prog = { 1 },
+                .result = ACCEPT,
+        },
+        {
+                "runtime/jit: pass > 32bit index to tail_call",
+                .insns = {
+                        BPF_LD_IMM64(BPF_REG_3, 0x100000000ULL),
+                        BPF_LD_MAP_FD(BPF_REG_2, 0),
+                        BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+                                     BPF_FUNC_tail_call),
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        BPF_EXIT_INSN(),
+                },
+                .fixup_prog = { 2 },
+                .result = ACCEPT,
+        },
+        {
                 "stack pointer arithmetic",
                 .insns = {
                         BPF_MOV64_IMM(BPF_REG_1, 4),
@@ -11137,6 +11163,64 @@ static struct bpf_test tests[] = {
                 .result = REJECT,
                 .prog_type = BPF_PROG_TYPE_TRACEPOINT,
         },
+        {
+                "xadd/w check unaligned stack",
+                .insns = {
+                        BPF_MOV64_IMM(BPF_REG_0, 1),
+                        BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -8),
+                        BPF_STX_XADD(BPF_W, BPF_REG_10, BPF_REG_0, -7),
+                        BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_10, -8),
+                        BPF_EXIT_INSN(),
+                },
+                .result = REJECT,
+                .errstr = "misaligned stack access off",
+                .prog_type = BPF_PROG_TYPE_SCHED_CLS,
+        },
+        {
+                "xadd/w check unaligned map",
+                .insns = {
+                        BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+                        BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+                        BPF_LD_MAP_FD(BPF_REG_1, 0),
+                        BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+                                     BPF_FUNC_map_lookup_elem),
+                        BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1),
+                        BPF_EXIT_INSN(),
+                        BPF_MOV64_IMM(BPF_REG_1, 1),
+                        BPF_STX_XADD(BPF_W, BPF_REG_0, BPF_REG_1, 3),
+                        BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_0, 3),
+                        BPF_EXIT_INSN(),
+                },
+                .fixup_map1 = { 3 },
+                .result = REJECT,
+                .errstr = "misaligned value access off",
+                .prog_type = BPF_PROG_TYPE_SCHED_CLS,
+        },
+        {
+                "xadd/w check unaligned pkt",
+                .insns = {
+                        BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+                                    offsetof(struct xdp_md, data)),
+                        BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+                                    offsetof(struct xdp_md, data_end)),
+                        BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+                        BPF_JMP_REG(BPF_JLT, BPF_REG_1, BPF_REG_3, 2),
+                        BPF_MOV64_IMM(BPF_REG_0, 99),
+                        BPF_JMP_IMM(BPF_JA, 0, 0, 6),
+                        BPF_MOV64_IMM(BPF_REG_0, 1),
+                        BPF_ST_MEM(BPF_W, BPF_REG_2, 0, 0),
+                        BPF_ST_MEM(BPF_W, BPF_REG_2, 3, 0),
+                        BPF_STX_XADD(BPF_W, BPF_REG_2, BPF_REG_0, 1),
+                        BPF_STX_XADD(BPF_W, BPF_REG_2, BPF_REG_0, 2),
+                        BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_2, 1),
+                        BPF_EXIT_INSN(),
+                },
+                .result = REJECT,
+                .errstr = "BPF_XADD stores into R2 packet",
+                .prog_type = BPF_PROG_TYPE_XDP,
+        },
 };
 
 static int probe_filter_length(const struct bpf_insn *fp)
diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_string.tc b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_string.tc
new file mode 100644
index 000000000000..5ba73035e1d9
--- /dev/null
+++ b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_string.tc
@@ -0,0 +1,46 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+# description: Kprobe event string type argument
+
+[ -f kprobe_events ] || exit_unsupported # this is configurable
+
+echo 0 > events/enable
+echo > kprobe_events
+
+case `uname -m` in
+x86_64)
+  ARG2=%si
+  OFFS=8
+;;
+i[3456]86)
+  ARG2=%cx
+  OFFS=4
+;;
+aarch64)
+  ARG2=%x1
+  OFFS=8
+;;
+arm*)
+  ARG2=%r1
+  OFFS=4
+;;
+*)
+  echo "Please implement other architecture here"
+  exit_untested
+esac
+
+: "Test get argument (1)"
+echo "p:testprobe create_trace_kprobe arg1=+0(+0(${ARG2})):string" > kprobe_events
+echo 1 > events/kprobes/testprobe/enable
+! echo test >> kprobe_events
+tail -n 1 trace | grep -qe "testprobe.* arg1=\"test\""
+
+echo 0 > events/kprobes/testprobe/enable
+: "Test get argument (2)"
+echo "p:testprobe create_trace_kprobe arg1=+0(+0(${ARG2})):string arg2=+0(+${OFFS}(${ARG2})):string" > kprobe_events
+echo 1 > events/kprobes/testprobe/enable
+! echo test1 test2 >> kprobe_events
+tail -n 1 trace | grep -qe "testprobe.* arg1=\"test1\" arg2=\"test2\""
+
+echo 0 > events/enable
+echo > kprobe_events
diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_syntax.tc b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_syntax.tc
new file mode 100644
index 000000000000..231bcd2c4eb5
--- /dev/null
+++ b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_syntax.tc
@@ -0,0 +1,97 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+# description: Kprobe event argument syntax
+
+[ -f kprobe_events ] || exit_unsupported # this is configurable
+
+grep "x8/16/32/64" README > /dev/null || exit_unsupported # version issue
+
+echo 0 > events/enable
+echo > kprobe_events
+
+PROBEFUNC="vfs_read"
+GOODREG=
+BADREG=
+GOODSYM="_sdata"
+if ! grep -qw ${GOODSYM} /proc/kallsyms ; then
+  GOODSYM=$PROBEFUNC
+fi
+BADSYM="deaqswdefr"
+SYMADDR=0x`grep -w ${GOODSYM} /proc/kallsyms | cut -f 1 -d " "`
+GOODTYPE="x16"
+BADTYPE="y16"
+
+case `uname -m` in
+x86_64|i[3456]86)
+  GOODREG=%ax
+  BADREG=%ex
+;;
+aarch64)
+  GOODREG=%x0
+  BADREG=%ax
+;;
+arm*)
+  GOODREG=%r0
+  BADREG=%ax
+;;
+esac
+
+test_goodarg() # Good-args
+{
+  while [ "$1" ]; do
+    echo "p ${PROBEFUNC} $1" > kprobe_events
+    shift 1
+  done;
+}
+
+test_badarg() # Bad-args
+{
+  while [ "$1" ]; do
+    ! echo "p ${PROBEFUNC} $1" > kprobe_events
+    shift 1
+  done;
+}
+
+echo > kprobe_events
+
+: "Register access"
+test_goodarg ${GOODREG}
+test_badarg ${BADREG}
+
+: "Symbol access"
+test_goodarg "@${GOODSYM}" "@${SYMADDR}" "@${GOODSYM}+10" "@${GOODSYM}-10"
+test_badarg "@" "@${BADSYM}" "@${GOODSYM}*10" "@${GOODSYM}/10" \
+            "@${GOODSYM}%10" "@${GOODSYM}&10" "@${GOODSYM}|10"
+
+: "Stack access"
+test_goodarg "\$stack" "\$stack0" "\$stack1"
+test_badarg "\$stackp" "\$stack0+10" "\$stack1-10"
+
+: "Retval access"
+echo "r ${PROBEFUNC} \$retval" > kprobe_events
+! echo "p ${PROBEFUNC} \$retval" > kprobe_events
+
+: "Comm access"
+test_goodarg "\$comm"
+
+: "Indirect memory access"
+test_goodarg "+0(${GOODREG})" "-0(${GOODREG})" "+10(\$stack)" \
+        "+0(\$stack1)" "+10(@${GOODSYM}-10)" "+0(+10(+20(\$stack)))"
+test_badarg "+(${GOODREG})" "(${GOODREG}+10)" "-(${GOODREG})" "(${GOODREG})" \
+        "+10(\$comm)" "+0(${GOODREG})+10"
+
+: "Name assignment"
+test_goodarg "varname=${GOODREG}"
+test_badarg "varname=varname2=${GOODREG}"
+
+: "Type syntax"
+test_goodarg "${GOODREG}:${GOODTYPE}"
+test_badarg "${GOODREG}::${GOODTYPE}" "${GOODREG}:${BADTYPE}" \
+        "${GOODTYPE}:${GOODREG}"
+
+: "Combination check"
+
+test_goodarg "\$comm:string" "+0(\$stack):string"
+test_badarg "\$comm:x64" "\$stack:string" "${GOODREG}:string"
+
+echo > kprobe_events
diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/probepoint.tc b/tools/testing/selftests/ftrace/test.d/kprobe/probepoint.tc
new file mode 100644
index 000000000000..4fda01a08da4
--- /dev/null
+++ b/tools/testing/selftests/ftrace/test.d/kprobe/probepoint.tc
@@ -0,0 +1,43 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+# description: Kprobe events - probe points
+
+[ -f kprobe_events ] || exit_unsupported # this is configurable
+
+TARGET_FUNC=create_trace_kprobe
+
+dec_addr() { # hexaddr
+  printf "%d" "0x"`echo $1 | tail -c 8`
+}
+
+set_offs() { # prev target next
+  A1=`dec_addr $1`
+  A2=`dec_addr $2`
+  A3=`dec_addr $3`
+  TARGET="0x$2" # an address
+  PREV=`expr $A1 - $A2` # offset to previous symbol
+  NEXT=+`expr $A3 - $A2` # offset to next symbol
+  OVERFLOW=+`printf "0x%x" ${PREV}` # overflow offset to previous symbol
+}
+
+# We have to decode symbol addresses to get correct offsets.
+# If the offset is not an instruction boundary, it cause -EILSEQ.
+set_offs `grep -A1 -B1 ${TARGET_FUNC} /proc/kallsyms | cut -f 1 -d " " | xargs`
+
+UINT_TEST=no
+# printf "%x" -1 returns (unsigned long)-1.
+if [ `printf "%x" -1 | wc -c` != 9 ]; then
+  UINT_TEST=yes
+fi
+
+echo 0 > events/enable
+echo > kprobe_events
+echo "p:testprobe ${TARGET_FUNC}" > kprobe_events
+echo "p:testprobe ${TARGET}" > kprobe_events
+echo "p:testprobe ${TARGET_FUNC}${NEXT}" > kprobe_events
+! echo "p:testprobe ${TARGET_FUNC}${PREV}" > kprobe_events
+if [ "${UINT_TEST}" = yes ]; then
+! echo "p:testprobe ${TARGET_FUNC}${OVERFLOW}" > kprobe_events
+fi
+echo > kprobe_events
+clear_trace
diff --git a/tools/testing/selftests/futex/Makefile b/tools/testing/selftests/futex/Makefile
index cea4adcd42b8..a63e8453984d 100644
--- a/tools/testing/selftests/futex/Makefile
+++ b/tools/testing/selftests/futex/Makefile
@@ -12,9 +12,9 @@ all:
                 BUILD_TARGET=$(OUTPUT)/$$DIR;   \
                 mkdir $$BUILD_TARGET  -p;       \
                 make OUTPUT=$$BUILD_TARGET -C $$DIR $@;\
-                if [ -e $$DIR/$(TEST_PROGS) ]; then
-                        rsync -a $$DIR/$(TEST_PROGS) $$BUILD_TARGET/;
-                fi
+                if [ -e $$DIR/$(TEST_PROGS) ]; then \
+                        rsync -a $$DIR/$(TEST_PROGS) $$BUILD_TARGET/; \
+                fi \
         done
 
 override define RUN_TESTS
diff --git a/tools/testing/selftests/memfd/Makefile b/tools/testing/selftests/memfd/Makefile
index a5276a91dfbf..0862e6f47a38 100644
--- a/tools/testing/selftests/memfd/Makefile
+++ b/tools/testing/selftests/memfd/Makefile
@@ -5,6 +5,7 @@ CFLAGS += -I../../../../include/
 CFLAGS += -I../../../../usr/include/
 
 TEST_PROGS := run_tests.sh
+TEST_FILES := run_fuse_test.sh
 TEST_GEN_FILES := memfd_test fuse_mnt fuse_test
 
 fuse_mnt.o: CFLAGS += $(shell pkg-config fuse --cflags)
diff --git a/tools/testing/selftests/memfd/config b/tools/testing/selftests/memfd/config
new file mode 100644
index 000000000000..835c7f4dadcd
--- /dev/null
+++ b/tools/testing/selftests/memfd/config
@@ -0,0 +1 @@
+CONFIG_FUSE_FS=m
diff --git a/tools/testing/selftests/memory-hotplug/Makefile b/tools/testing/selftests/memory-hotplug/Makefile
index 86636d207adf..686da510f989 100644
--- a/tools/testing/selftests/memory-hotplug/Makefile
+++ b/tools/testing/selftests/memory-hotplug/Makefile
@@ -4,8 +4,9 @@ all:
 include ../lib.mk
 
 TEST_PROGS := mem-on-off-test.sh
-override RUN_TESTS := ./mem-on-off-test.sh -r 2 && echo "selftests: memory-hotplug [PASS]" || echo "selftests: memory-hotplug [FAIL]"
-override EMIT_TESTS := echo "$(RUN_TESTS)"
+override RUN_TESTS := @./mem-on-off-test.sh -r 2 && echo "selftests: memory-hotplug [PASS]" || echo "selftests: memory-hotplug [FAIL]"
+
+override EMIT_TESTS := echo "$(subst @,,$(RUN_TESTS))"
 
 run_full_test:
         @/bin/bash ./mem-on-off-test.sh && echo "memory-hotplug selftests: [PASS]" || echo "memory-hotplug selftests: [FAIL]"
diff --git a/tools/testing/selftests/powerpc/alignment/alignment_handler.c b/tools/testing/selftests/powerpc/alignment/alignment_handler.c
index 39fd362415cf..0f2698f9fd6d 100644
--- a/tools/testing/selftests/powerpc/alignment/alignment_handler.c
+++ b/tools/testing/selftests/powerpc/alignment/alignment_handler.c
@@ -57,7 +57,7 @@ volatile int gotsig;
 
 void sighandler(int sig, siginfo_t *info, void *ctx)
 {
-        struct ucontext *ucp = ctx;
+        ucontext_t *ucp = ctx;
 
         if (!testing) {
                 signal(sig, SIG_DFL);
diff --git a/tools/testing/selftests/powerpc/mm/subpage_prot.c b/tools/testing/selftests/powerpc/mm/subpage_prot.c
index 35ade7406dcd..3ae77ba93208 100644
--- a/tools/testing/selftests/powerpc/mm/subpage_prot.c
+++ b/tools/testing/selftests/powerpc/mm/subpage_prot.c
@@ -135,6 +135,16 @@ static int run_test(void *addr, unsigned long size)
         return 0;
 }
 
+static int syscall_available(void)
+{
+        int rc;
+
+        errno = 0;
+        rc = syscall(__NR_subpage_prot, 0, 0, 0);
+
+        return rc == 0 || (errno != ENOENT && errno != ENOSYS);
+}
+
 int test_anon(void)
 {
         unsigned long align;
@@ -145,6 +155,8 @@ int test_anon(void)
         void *mallocblock;
         unsigned long mallocsize;
 
+        SKIP_IF(!syscall_available());
+
         if (getpagesize() != 0x10000) {
                 fprintf(stderr, "Kernel page size must be 64K!\n");
                 return 1;
@@ -180,6 +192,8 @@ int test_file(void)
         off_t filesize;
         int fd;
 
+        SKIP_IF(!syscall_available());
+
         fd = open(file_name, O_RDWR);
         if (fd == -1) {
                 perror("failed to open file");
diff --git a/tools/testing/selftests/powerpc/tm/Makefile b/tools/testing/selftests/powerpc/tm/Makefile
index a23453943ad2..5c72ff978f27 100644
--- a/tools/testing/selftests/powerpc/tm/Makefile
+++ b/tools/testing/selftests/powerpc/tm/Makefile
@@ -16,7 +16,7 @@ $(OUTPUT)/tm-syscall: tm-syscall-asm.S
 $(OUTPUT)/tm-syscall: CFLAGS += -I../../../../../usr/include
 $(OUTPUT)/tm-tmspr: CFLAGS += -pthread
 $(OUTPUT)/tm-vmx-unavail: CFLAGS += -pthread -m64
-$(OUTPUT)/tm-resched-dscr: ../pmu/lib.o
+$(OUTPUT)/tm-resched-dscr: ../pmu/lib.c
 $(OUTPUT)/tm-unavailable: CFLAGS += -O0 -pthread -m64 -Wno-error=uninitialized -mvsx
 $(OUTPUT)/tm-trap: CFLAGS += -O0 -pthread -m64
 
diff --git a/tools/testing/selftests/powerpc/tm/tm-trap.c b/tools/testing/selftests/powerpc/tm/tm-trap.c
index 5d92c23ee6cb..179d592f0073 100644
--- a/tools/testing/selftests/powerpc/tm/tm-trap.c
+++ b/tools/testing/selftests/powerpc/tm/tm-trap.c
@@ -255,6 +255,8 @@ int tm_trap_test(void)
 
         struct sigaction trap_sa;
 
+        SKIP_IF(!have_htm());
+
         trap_sa.sa_flags = SA_SIGINFO;
         trap_sa.sa_sigaction = trap_signal_handler;
         sigaction(SIGTRAP, &trap_sa, NULL);
diff --git a/tools/testing/selftests/pstore/config b/tools/testing/selftests/pstore/config
index 6a8e5a9bfc10..d148f9f89fb6 100644
--- a/tools/testing/selftests/pstore/config
+++ b/tools/testing/selftests/pstore/config
@@ -2,3 +2,4 @@ CONFIG_MISC_FILESYSTEMS=y
 CONFIG_PSTORE=y
 CONFIG_PSTORE_PMSG=y
 CONFIG_PSTORE_CONSOLE=y
+CONFIG_PSTORE_RAM=m
diff --git a/tools/testing/selftests/seccomp/seccomp_bpf.c b/tools/testing/selftests/seccomp/seccomp_bpf.c
index 0b457e8e0f0c..5df609950a66 100644
--- a/tools/testing/selftests/seccomp/seccomp_bpf.c
+++ b/tools/testing/selftests/seccomp/seccomp_bpf.c
@@ -141,6 +141,15 @@ struct seccomp_data {
 #define SECCOMP_FILTER_FLAG_LOG 2
 #endif
 
+#ifndef PTRACE_SECCOMP_GET_METADATA
+#define PTRACE_SECCOMP_GET_METADATA     0x420d
+
+struct seccomp_metadata {
+        __u64 filter_off;       /* Input: which filter */
+        __u64 flags;             /* Output: filter's flags */
+};
+#endif
+
 #ifndef seccomp
 int seccomp(unsigned int op, unsigned int flags, void *args)
 {
@@ -2845,6 +2854,58 @@ TEST(get_action_avail)
         EXPECT_EQ(errno, EOPNOTSUPP);
 }
 
+TEST(get_metadata)
+{
+        pid_t pid;
+        int pipefd[2];
+        char buf;
+        struct seccomp_metadata md;
+
+        ASSERT_EQ(0, pipe(pipefd));
+
+        pid = fork();
+        ASSERT_GE(pid, 0);
+        if (pid == 0) {
+                struct sock_filter filter[] = {
+                        BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ALLOW),
+                };
+                struct sock_fprog prog = {
+                        .len = (unsigned short)ARRAY_SIZE(filter),
+                        .filter = filter,
+                };
+
+                /* one with log, one without */
+                ASSERT_EQ(0, seccomp(SECCOMP_SET_MODE_FILTER,
+                                     SECCOMP_FILTER_FLAG_LOG, &prog));
+                ASSERT_EQ(0, seccomp(SECCOMP_SET_MODE_FILTER, 0, &prog));
+
+                ASSERT_EQ(0, close(pipefd[0]));
+                ASSERT_EQ(1, write(pipefd[1], "1", 1));
+                ASSERT_EQ(0, close(pipefd[1]));
+
+                while (1)
+                        sleep(100);
+        }
+
+        ASSERT_EQ(0, close(pipefd[1]));
+        ASSERT_EQ(1, read(pipefd[0], &buf, 1));
+
+        ASSERT_EQ(0, ptrace(PTRACE_ATTACH, pid));
+        ASSERT_EQ(pid, waitpid(pid, NULL, 0));
+
+        md.filter_off = 0;
+        ASSERT_EQ(sizeof(md), ptrace(PTRACE_SECCOMP_GET_METADATA, pid, sizeof(md), &md));
+        EXPECT_EQ(md.flags, SECCOMP_FILTER_FLAG_LOG);
+        EXPECT_EQ(md.filter_off, 0);
+
+        md.filter_off = 1;
+        ASSERT_EQ(sizeof(md), ptrace(PTRACE_SECCOMP_GET_METADATA, pid, sizeof(md), &md));
+        EXPECT_EQ(md.flags, 0);
+        EXPECT_EQ(md.filter_off, 1);
+
+        ASSERT_EQ(0, kill(pid, SIGKILL));
+}
+
 /*
  * TODO:
  * - add microbenchmarks
diff --git a/tools/testing/selftests/sync/Makefile b/tools/testing/selftests/sync/Makefile
index b3c8ba3cb668..d0121a8a3523 100644
--- a/tools/testing/selftests/sync/Makefile
+++ b/tools/testing/selftests/sync/Makefile
@@ -30,7 +30,7 @@ $(TEST_CUSTOM_PROGS): $(TESTS) $(OBJS)
         $(CC) -o $(TEST_CUSTOM_PROGS) $(OBJS) $(TESTS) $(CFLAGS) $(LDFLAGS)
 
 $(OBJS): $(OUTPUT)/%.o: %.c
-        $(CC) -c $^ -o $@
+        $(CC) -c $^ -o $@ $(CFLAGS)
 
 $(TESTS): $(OUTPUT)/%.o: %.c
         $(CC) -c $^ -o $@
diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/skbmod.json b/tools/testing/selftests/tc-testing/tc-tests/actions/skbmod.json
index e34075059c26..90bba48c3f07 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/actions/skbmod.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/actions/skbmod.json
@@ -315,7 +315,7 @@
         "cmdUnderTest": "$TC actions ls action skbmod",
         "expExitCode": "0",
         "verifyCmd": "$TC actions get action skbmod index 4",
-        "matchPattern": "action order [0-9]*: skbmod pipe set etype 0x0031",
+        "matchPattern": "action order [0-9]*: skbmod pipe set etype 0x31",
         "matchCount": "1",
         "teardown": [
             "$TC actions flush action skbmod"
diff --git a/tools/testing/selftests/vDSO/Makefile b/tools/testing/selftests/vDSO/Makefile
index 3d5a62ff7d31..f5d7a7851e21 100644
--- a/tools/testing/selftests/vDSO/Makefile
+++ b/tools/testing/selftests/vDSO/Makefile
@@ -1,4 +1,6 @@
 # SPDX-License-Identifier: GPL-2.0
+include ../lib.mk
+
 ifndef CROSS_COMPILE
 CFLAGS := -std=gnu99
 CFLAGS_vdso_standalone_test_x86 := -nostdlib -fno-asynchronous-unwind-tables -fno-stack-protector
@@ -6,16 +8,14 @@ ifeq ($(CONFIG_X86_32),y)
 LDLIBS += -lgcc_s
 endif
 
-TEST_PROGS := vdso_test vdso_standalone_test_x86
+TEST_PROGS := $(OUTPUT)/vdso_test $(OUTPUT)/vdso_standalone_test_x86
 
 all: $(TEST_PROGS)
-vdso_test: parse_vdso.c vdso_test.c
-vdso_standalone_test_x86: vdso_standalone_test_x86.c parse_vdso.c
+$(OUTPUT)/vdso_test: parse_vdso.c vdso_test.c
+$(OUTPUT)/vdso_standalone_test_x86: vdso_standalone_test_x86.c parse_vdso.c
         $(CC) $(CFLAGS) $(CFLAGS_vdso_standalone_test_x86) \
                 vdso_standalone_test_x86.c parse_vdso.c \
-                -o vdso_standalone_test_x86
+                -o $@
 
-include ../lib.mk
-clean:
-        rm -fr $(TEST_PROGS)
+EXTRA_CLEAN := $(TEST_PROGS)
 endif
diff --git a/tools/testing/selftests/vm/.gitignore b/tools/testing/selftests/vm/.gitignore
index 63c94d776e89..342c7bc9dc8c 100644
--- a/tools/testing/selftests/vm/.gitignore
+++ b/tools/testing/selftests/vm/.gitignore
@@ -11,3 +11,4 @@ mlock-intersect-test
 mlock-random-test
 virtual_address_range
 gup_benchmark
+va_128TBswitch
diff --git a/tools/testing/selftests/vm/run_vmtests b/tools/testing/selftests/vm/run_vmtests
index d2561895a021..22d564673830 100755
--- a/tools/testing/selftests/vm/run_vmtests
+++ b/tools/testing/selftests/vm/run_vmtests
@@ -2,25 +2,33 @@
 # SPDX-License-Identifier: GPL-2.0
 #please run as root
 
-#we need 256M, below is the size in kB
-needmem=262144
 mnt=./huge
 exitcode=0
 
-#get pagesize and freepages from /proc/meminfo
+#get huge pagesize and freepages from /proc/meminfo
 while read name size unit; do
         if [ "$name" = "HugePages_Free:" ]; then
                 freepgs=$size
         fi
         if [ "$name" = "Hugepagesize:" ]; then
-                pgsize=$size
+                hpgsize_KB=$size
         fi
 done < /proc/meminfo
 
+# Simple hugetlbfs tests have a hardcoded minimum requirement of
+# huge pages totaling 256MB (262144KB) in size.  The userfaultfd
+# hugetlb test requires a minimum of 2 * nr_cpus huge pages.  Take
+# both of these requirements into account and attempt to increase
+# number of huge pages available.
+nr_cpus=$(nproc)
+hpgsize_MB=$((hpgsize_KB / 1024))
+half_ufd_size_MB=$((((nr_cpus * hpgsize_MB + 127) / 128) * 128))
+needmem_KB=$((half_ufd_size_MB * 2 * 1024))
+
 #set proper nr_hugepages
-if [ -n "$freepgs" ] && [ -n "$pgsize" ]; then
+if [ -n "$freepgs" ] && [ -n "$hpgsize_KB" ]; then
         nr_hugepgs=`cat /proc/sys/vm/nr_hugepages`
-        needpgs=`expr $needmem / $pgsize`
+        needpgs=$((needmem_KB / hpgsize_KB))
         tries=2
         while [ $tries -gt 0 ] && [ $freepgs -lt $needpgs ]; do
                 lackpgs=$(( $needpgs - $freepgs ))
@@ -107,8 +115,9 @@ fi
 echo "---------------------------"
 echo "running userfaultfd_hugetlb"
 echo "---------------------------"
-# 256MB total huge pages == 128MB src and 128MB dst
-./userfaultfd hugetlb 128 32 $mnt/ufd_test_file
+# Test requires source and destination huge pages.  Size of source
+# (half_ufd_size_MB) is passed as argument to test.
+./userfaultfd hugetlb $half_ufd_size_MB 32 $mnt/ufd_test_file
 if [ $? -ne 0 ]; then
         echo "[FAIL]"
         exitcode=1
diff --git a/tools/testing/selftests/x86/Makefile b/tools/testing/selftests/x86/Makefile
index 10ca46df1449..d744991c0f4f 100644
--- a/tools/testing/selftests/x86/Makefile
+++ b/tools/testing/selftests/x86/Makefile
@@ -5,16 +5,26 @@ include ../lib.mk
 
 .PHONY: all all_32 all_64 warn_32bit_failure clean
 
-TARGETS_C_BOTHBITS := single_step_syscall sysret_ss_attrs syscall_nt ptrace_syscall test_mremap_vdso \
-                        check_initial_reg_state sigreturn ldt_gdt iopl mpx-mini-test ioperm \
+UNAME_M := $(shell uname -m)
+CAN_BUILD_I386 := $(shell ./check_cc.sh $(CC) trivial_32bit_program.c -m32)
+CAN_BUILD_X86_64 := $(shell ./check_cc.sh $(CC) trivial_64bit_program.c)
+
+TARGETS_C_BOTHBITS := single_step_syscall sysret_ss_attrs syscall_nt test_mremap_vdso \
+                        check_initial_reg_state sigreturn iopl mpx-mini-test ioperm \
                         protection_keys test_vdso test_vsyscall
 TARGETS_C_32BIT_ONLY := entry_from_vm86 syscall_arg_fault test_syscall_vdso unwind_vdso \
                         test_FCMOV test_FCOMI test_FISTTP \
                         vdso_restorer
-TARGETS_C_64BIT_ONLY := fsgsbase sysret_rip 5lvl
+TARGETS_C_64BIT_ONLY := fsgsbase sysret_rip
+# Some selftests require 32bit support enabled also on 64bit systems
+TARGETS_C_32BIT_NEEDED := ldt_gdt ptrace_syscall
 
-TARGETS_C_32BIT_ALL := $(TARGETS_C_BOTHBITS) $(TARGETS_C_32BIT_ONLY)
+TARGETS_C_32BIT_ALL := $(TARGETS_C_BOTHBITS) $(TARGETS_C_32BIT_ONLY) $(TARGETS_C_32BIT_NEEDED)
 TARGETS_C_64BIT_ALL := $(TARGETS_C_BOTHBITS) $(TARGETS_C_64BIT_ONLY)
+ifeq ($(CAN_BUILD_I386)$(CAN_BUILD_X86_64),11)
+TARGETS_C_64BIT_ALL += $(TARGETS_C_32BIT_NEEDED)
+endif
+
 BINARIES_32 := $(TARGETS_C_32BIT_ALL:%=%_32)
 BINARIES_64 := $(TARGETS_C_64BIT_ALL:%=%_64)
 
@@ -23,10 +33,6 @@ BINARIES_64 := $(patsubst %,$(OUTPUT)/%,$(BINARIES_64))
 
 CFLAGS := -O2 -g -std=gnu99 -pthread -Wall -no-pie
 
-UNAME_M := $(shell uname -m)
-CAN_BUILD_I386 := $(shell ./check_cc.sh $(CC) trivial_32bit_program.c -m32)
-CAN_BUILD_X86_64 := $(shell ./check_cc.sh $(CC) trivial_64bit_program.c)
-
 define gen-target-rule-32
 $(1) $(1)_32: $(OUTPUT)/$(1)_32
 .PHONY: $(1) $(1)_32
@@ -40,12 +46,14 @@ endef
 ifeq ($(CAN_BUILD_I386),1)
 all: all_32
 TEST_PROGS += $(BINARIES_32)
+EXTRA_CFLAGS += -DCAN_BUILD_32
 $(foreach t,$(TARGETS_C_32BIT_ALL),$(eval $(call gen-target-rule-32,$(t))))
 endif
 
 ifeq ($(CAN_BUILD_X86_64),1)
 all: all_64
 TEST_PROGS += $(BINARIES_64)
+EXTRA_CFLAGS += -DCAN_BUILD_64
 $(foreach t,$(TARGETS_C_64BIT_ALL),$(eval $(call gen-target-rule-64,$(t))))
 endif
 
diff --git a/tools/testing/selftests/x86/entry_from_vm86.c b/tools/testing/selftests/x86/entry_from_vm86.c
index 361466a2eaef..ade443a88421 100644
--- a/tools/testing/selftests/x86/entry_from_vm86.c
+++ b/tools/testing/selftests/x86/entry_from_vm86.c
@@ -95,6 +95,10 @@ asm (
         "int3\n\t"
         "vmcode_int80:\n\t"
         "int $0x80\n\t"
+        "vmcode_popf_hlt:\n\t"
+        "push %ax\n\t"
+        "popf\n\t"
+        "hlt\n\t"
         "vmcode_umip:\n\t"
         /* addressing via displacements */
         "smsw (2052)\n\t"
@@ -124,8 +128,8 @@ asm (
 
 extern unsigned char vmcode[], end_vmcode[];
 extern unsigned char vmcode_bound[], vmcode_sysenter[], vmcode_syscall[],
-        vmcode_sti[], vmcode_int3[], vmcode_int80[], vmcode_umip[],
-        vmcode_umip_str[], vmcode_umip_sldt[];
+        vmcode_sti[], vmcode_int3[], vmcode_int80[], vmcode_popf_hlt[],
+        vmcode_umip[], vmcode_umip_str[], vmcode_umip_sldt[];
 
 /* Returns false if the test was skipped. */
 static bool do_test(struct vm86plus_struct *v86, unsigned long eip,
@@ -175,7 +179,7 @@ static bool do_test(struct vm86plus_struct *v86, unsigned long eip,
             (VM86_TYPE(ret) == rettype && VM86_ARG(ret) == retarg)) {
                 printf("[OK]\tReturned correctly\n");
         } else {
-                printf("[FAIL]\tIncorrect return reason\n");
+                printf("[FAIL]\tIncorrect return reason (started at eip = 0x%lx, ended at eip = 0x%lx)\n", eip, v86->regs.eip);
                 nerrs++;
         }
 
@@ -264,6 +268,9 @@ int main(void)
         v86.regs.ds = load_addr / 16;
         v86.regs.es = load_addr / 16;
 
+        /* Use the end of the page as our stack. */
+        v86.regs.esp = 4096;
+
         assert((v86.regs.cs & 3) == 0); /* Looks like RPL = 0 */
 
         /* #BR -- should deliver SIG??? */
@@ -295,6 +302,23 @@ int main(void)
         v86.regs.eflags &= ~X86_EFLAGS_IF;
         do_test(&v86, vmcode_sti - vmcode, VM86_STI, 0, "STI with VIP set");
 
+        /* POPF with VIP set but IF clear: should not trap */
+        v86.regs.eflags = X86_EFLAGS_VIP;
+        v86.regs.eax = 0;
+        do_test(&v86, vmcode_popf_hlt - vmcode, VM86_UNKNOWN, 0, "POPF with VIP set and IF clear");
+
+        /* POPF with VIP set and IF set: should trap */
+        v86.regs.eflags = X86_EFLAGS_VIP;
+        v86.regs.eax = X86_EFLAGS_IF;
+        do_test(&v86, vmcode_popf_hlt - vmcode, VM86_STI, 0, "POPF with VIP and IF set");
+
+        /* POPF with VIP clear and IF set: should not trap */
+        v86.regs.eflags = 0;
+        v86.regs.eax = X86_EFLAGS_IF;
+        do_test(&v86, vmcode_popf_hlt - vmcode, VM86_UNKNOWN, 0, "POPF with VIP clear and IF set");
+
+        v86.regs.eflags = 0;
+
         /* INT3 -- should cause #BP */
         do_test(&v86, vmcode_int3 - vmcode, VM86_TRAP, 3, "INT3");
 
@@ -318,7 +342,7 @@ int main(void)
         clearhandler(SIGSEGV);
 
         /* Make sure nothing explodes if we fork. */
-        if (fork() > 0)
+        if (fork() == 0)
                 return 0;
 
         return (nerrs == 0 ? 0 : 1);
diff --git a/tools/testing/selftests/x86/mpx-mini-test.c b/tools/testing/selftests/x86/mpx-mini-test.c
index ec0f6b45ce8b..9c0325e1ea68 100644
--- a/tools/testing/selftests/x86/mpx-mini-test.c
+++ b/tools/testing/selftests/x86/mpx-mini-test.c
@@ -315,11 +315,39 @@ static inline void *__si_bounds_upper(siginfo_t *si)
         return si->si_upper;
 }
 #else
+
+/*
+ * This deals with old version of _sigfault in some distros:
+ *
+
+old _sigfault:
+        struct {
+            void *si_addr;
+        } _sigfault;
+
+new _sigfault:
+        struct {
+                void __user *_addr;
+                int _trapno;
+                short _addr_lsb;
+                union {
+                        struct {
+                                void __user *_lower;
+                                void __user *_upper;
+                        } _addr_bnd;
+                        __u32 _pkey;
+                };
+        } _sigfault;
+ *
+ */
+
 static inline void **__si_bounds_hack(siginfo_t *si)
 {
         void *sigfault = &si->_sifields._sigfault;
         void *end_sigfault = sigfault + sizeof(si->_sifields._sigfault);
-        void **__si_lower = end_sigfault;
+        int *trapno = (int*)end_sigfault;
+        /* skip _trapno and _addr_lsb */
+        void **__si_lower = (void**)(trapno + 2);
 
         return __si_lower;
 }
@@ -331,7 +359,7 @@ static inline void *__si_bounds_lower(siginfo_t *si)
 
 static inline void *__si_bounds_upper(siginfo_t *si)
 {
-        return (*__si_bounds_hack(si)) + sizeof(void *);
+        return *(__si_bounds_hack(si) + 1);
 }
 #endif
 
diff --git a/tools/testing/selftests/x86/protection_keys.c b/tools/testing/selftests/x86/protection_keys.c
index bc1b0735bb50..f15aa5a76fe3 100644
--- a/tools/testing/selftests/x86/protection_keys.c
+++ b/tools/testing/selftests/x86/protection_keys.c
@@ -393,34 +393,6 @@ pid_t fork_lazy_child(void)
         return forkret;
 }
 
-void davecmp(void *_a, void *_b, int len)
-{
-        int i;
-        unsigned long *a = _a;
-        unsigned long *b = _b;
-
-        for (i = 0; i < len / sizeof(*a); i++) {
-                if (a[i] == b[i])
-                        continue;
-
-                dprintf3("[%3d]: a: %016lx b: %016lx\n", i, a[i], b[i]);
-        }
-}
-
-void dumpit(char *f)
-{
-        int fd = open(f, O_RDONLY);
-        char buf[100];
-        int nr_read;
-
-        dprintf2("maps fd: %d\n", fd);
-        do {
-                nr_read = read(fd, &buf[0], sizeof(buf));
-                write(1, buf, nr_read);
-        } while (nr_read > 0);
-        close(fd);
-}
-
 #define PKEY_DISABLE_ACCESS    0x1
 #define PKEY_DISABLE_WRITE     0x2
 
diff --git a/tools/testing/selftests/x86/ptrace_syscall.c b/tools/testing/selftests/x86/ptrace_syscall.c
index 1ae1c5a7392e..6f22238f3217 100644
--- a/tools/testing/selftests/x86/ptrace_syscall.c
+++ b/tools/testing/selftests/x86/ptrace_syscall.c
@@ -183,8 +183,10 @@ static void test_ptrace_syscall_restart(void)
                 if (ptrace(PTRACE_TRACEME, 0, 0, 0) != 0)
                         err(1, "PTRACE_TRACEME");
 
+                pid_t pid = getpid(), tid = syscall(SYS_gettid);
+
                 printf("\tChild will make one syscall\n");
-                raise(SIGSTOP);
+                syscall(SYS_tgkill, pid, tid, SIGSTOP);
 
                 syscall(SYS_gettid, 10, 11, 12, 13, 14, 15);
                 _exit(0);
@@ -301,9 +303,11 @@ static void test_restart_under_ptrace(void)
                 if (ptrace(PTRACE_TRACEME, 0, 0, 0) != 0)
                         err(1, "PTRACE_TRACEME");
 
+                pid_t pid = getpid(), tid = syscall(SYS_gettid);
+
                 printf("\tChild will take a nap until signaled\n");
                 setsigign(SIGUSR1, SA_RESTART);
-                raise(SIGSTOP);
+                syscall(SYS_tgkill, pid, tid, SIGSTOP);
 
                 syscall(SYS_pause, 0, 0, 0, 0, 0, 0);
                 _exit(0);
diff --git a/tools/testing/selftests/x86/single_step_syscall.c b/tools/testing/selftests/x86/single_step_syscall.c
index a48da95c18fd..ddfdd635de16 100644
--- a/tools/testing/selftests/x86/single_step_syscall.c
+++ b/tools/testing/selftests/x86/single_step_syscall.c
@@ -119,7 +119,9 @@ static void check_result(void)
 
 int main()
 {
+#ifdef CAN_BUILD_32
         int tmp;
+#endif
 
         sethandler(SIGTRAP, sigtrap, 0);
 
@@ -139,12 +141,13 @@ int main()
                       : : "c" (post_nop) : "r11");
         check_result();
 #endif
-
+#ifdef CAN_BUILD_32
         printf("[RUN]\tSet TF and check int80\n");
         set_eflags(get_eflags() | X86_EFLAGS_TF);
         asm volatile ("int $0x80" : "=a" (tmp) : "a" (SYS_getpid)
                         : INT80_CLOBBERS);
         check_result();
+#endif
 
         /*
          * This test is particularly interesting if fast syscalls use
diff --git a/tools/testing/selftests/x86/test_mremap_vdso.c b/tools/testing/selftests/x86/test_mremap_vdso.c
index bf0d687c7db7..64f11c8d9b76 100644
--- a/tools/testing/selftests/x86/test_mremap_vdso.c
+++ b/tools/testing/selftests/x86/test_mremap_vdso.c
@@ -90,8 +90,12 @@ int main(int argc, char **argv, char **envp)
                         vdso_size += PAGE_SIZE;
                 }
 
+#ifdef __i386__
                 /* Glibc is likely to explode now - exit with raw syscall */
                 asm volatile ("int $0x80" : : "a" (__NR_exit), "b" (!!ret));
+#else /* __x86_64__ */
+                syscall(SYS_exit, ret);
+#endif
         } else {
                 int status;
 
diff --git a/tools/testing/selftests/x86/test_vdso.c b/tools/testing/selftests/x86/test_vdso.c
index 29973cde06d3..235259011704 100644
--- a/tools/testing/selftests/x86/test_vdso.c
+++ b/tools/testing/selftests/x86/test_vdso.c
@@ -26,20 +26,59 @@
 # endif
 #endif
 
+/* max length of lines in /proc/self/maps - anything longer is skipped here */
+#define MAPS_LINE_LEN 128
+
 int nerrs = 0;
 
+typedef long (*getcpu_t)(unsigned *, unsigned *, void *);
+
+getcpu_t vgetcpu;
+getcpu_t vdso_getcpu;
+
+static void *vsyscall_getcpu(void)
+{
 #ifdef __x86_64__
-# define VSYS(x) (x)
+        FILE *maps;
+        char line[MAPS_LINE_LEN];
+        bool found = false;
+
+        maps = fopen("/proc/self/maps", "r");
+        if (!maps) /* might still be present, but ignore it here, as we test vDSO not vsyscall */
+                return NULL;
+
+        while (fgets(line, MAPS_LINE_LEN, maps)) {
+                char r, x;
+                void *start, *end;
+                char name[MAPS_LINE_LEN];
+
+                /* sscanf() is safe here as strlen(name) >= strlen(line) */
+                if (sscanf(line, "%p-%p %c-%cp %*x %*x:%*x %*u %s",
+                           &start, &end, &r, &x, name) != 5)
+                        continue;
+
+                if (strcmp(name, "[vsyscall]"))
+                        continue;
+
+                /* assume entries are OK, as we test vDSO here not vsyscall */
+                found = true;
+                break;
+        }
+
+        fclose(maps);
+
+        if (!found) {
+                printf("Warning: failed to find vsyscall getcpu\n");
+                return NULL;
+        }
+        return (void *) (0xffffffffff600800);
 #else
-# define VSYS(x) 0
+        return NULL;
 #endif
+}
 
-typedef long (*getcpu_t)(unsigned *, unsigned *, void *);
-
-const getcpu_t vgetcpu = (getcpu_t)VSYS(0xffffffffff600800);
-getcpu_t vdso_getcpu;
 
-void fill_function_pointers()
+static void fill_function_pointers()
 {
         void *vdso = dlopen("linux-vdso.so.1",
                             RTLD_LAZY | RTLD_LOCAL | RTLD_NOLOAD);
@@ -54,6 +93,8 @@ void fill_function_pointers()
         vdso_getcpu = (getcpu_t)dlsym(vdso, "__vdso_getcpu");
         if (!vdso_getcpu)
                 printf("Warning: failed to find getcpu in vDSO\n");
+
+        vgetcpu = (getcpu_t) vsyscall_getcpu();
 }
 
 static long sys_getcpu(unsigned * cpu, unsigned * node,
diff --git a/tools/testing/selftests/x86/test_vsyscall.c b/tools/testing/selftests/x86/test_vsyscall.c
index 7a744fa7b786..0b4f1cc2291c 100644
--- a/tools/testing/selftests/x86/test_vsyscall.c
+++ b/tools/testing/selftests/x86/test_vsyscall.c
@@ -33,6 +33,9 @@
 # endif
 #endif
 
+/* max length of lines in /proc/self/maps - anything longer is skipped here */
+#define MAPS_LINE_LEN 128
+
 static void sethandler(int sig, void (*handler)(int, siginfo_t *, void *),
                        int flags)
 {
@@ -98,7 +101,7 @@ static int init_vsys(void)
 #ifdef __x86_64__
         int nerrs = 0;
         FILE *maps;
-        char line[128];
+        char line[MAPS_LINE_LEN];
         bool found = false;
 
         maps = fopen("/proc/self/maps", "r");
@@ -108,10 +111,12 @@ static int init_vsys(void)
                 return 0;
         }
 
-        while (fgets(line, sizeof(line), maps)) {
+        while (fgets(line, MAPS_LINE_LEN, maps)) {
                 char r, x;
                 void *start, *end;
-                char name[128];
+                char name[MAPS_LINE_LEN];
+
+                /* sscanf() is safe here as strlen(name) >= strlen(line) */
                 if (sscanf(line, "%p-%p %c-%cp %*x %*x:%*x %*u %s",
                            &start, &end, &r, &x, name) != 5)
                         continue;
@@ -445,7 +450,7 @@ static void sigtrap(int sig, siginfo_t *info, void *ctx_void)
                 num_vsyscall_traps++;
 }
 
-static int test_native_vsyscall(void)
+static int test_emulation(void)
 {
         time_t tmp;
         bool is_native;
@@ -453,7 +458,7 @@ static int test_native_vsyscall(void)
         if (!vtime)
                 return 0;
 
-        printf("[RUN]\tchecking for native vsyscall\n");
+        printf("[RUN]\tchecking that vsyscalls are emulated\n");
         sethandler(SIGTRAP, sigtrap, 0);
         set_eflags(get_eflags() | X86_EFLAGS_TF);
         vtime(&tmp);
@@ -469,11 +474,12 @@ static int test_native_vsyscall(void)
          */
         is_native = (num_vsyscall_traps > 1);
 
-        printf("\tvsyscalls are %s (%d instructions in vsyscall page)\n",
+        printf("[%s]\tvsyscalls are %s (%d instructions in vsyscall page)\n",
+               (is_native ? "FAIL" : "OK"),
                (is_native ? "native" : "emulated"),
                (int)num_vsyscall_traps);
 
-        return 0;
+        return is_native;
 }
 #endif
 
@@ -493,7 +499,7 @@ int main(int argc, char **argv)
         nerrs += test_vsys_r();
 
 #ifdef __x86_64__
-        nerrs += test_native_vsyscall();
+        nerrs += test_emulation();
 #endif
 
         return nerrs ? 1 : 0;
diff --git a/tools/usb/Makefile b/tools/usb/Makefile
index 4e6506078494..01d758d73b6d 100644
--- a/tools/usb/Makefile
+++ b/tools/usb/Makefile
@@ -1,7 +1,6 @@
 # SPDX-License-Identifier: GPL-2.0
 # Makefile for USB tools
 
-CC = $(CROSS_COMPILE)gcc
 PTHREAD_LIBS = -lpthread
 WARNINGS = -Wall -Wextra
 CFLAGS = $(WARNINGS) -g -I../include
diff --git a/tools/vm/Makefile b/tools/vm/Makefile
index be320b905ea7..20f6cf04377f 100644
--- a/tools/vm/Makefile
+++ b/tools/vm/Makefile
@@ -6,7 +6,6 @@ TARGETS=page-types slabinfo page_owner_sort
 LIB_DIR = ../lib/api
 LIBS = $(LIB_DIR)/libapi.a
 
-CC = $(CROSS_COMPILE)gcc
 CFLAGS = -Wall -Wextra -I../lib/
 LDFLAGS = $(LIBS)
 
diff --git a/tools/wmi/Makefile b/tools/wmi/Makefile
index e664f1167388..e0e87239126b 100644
--- a/tools/wmi/Makefile
+++ b/tools/wmi/Makefile
@@ -2,7 +2,6 @@ PREFIX ?= /usr
 SBINDIR ?= sbin
 INSTALL ?= install
 CFLAGS += -D__EXPORTED_HEADERS__ -I../../include/uapi -I../../include
-CC = $(CROSS_COMPILE)gcc
 
 TARGET = dell-smbios-example